diff --git a/README.md b/README.md
index 30e1c73..5bae0a1 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,9 @@
+
+> [!NOTE]
+> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。
+> [English](./README.en.md) · [原始项目](https://github.com/dmlc/dgl) · [上游 README](https://github.com/dmlc/dgl/blob/HEAD/README.md)
+> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
+
@@ -11,305 +17,306 @@
[Website](https://www.dgl.ai) | [A Blitz Introduction to DGL](https://docs.dgl.ai/tutorials/blitz/index.html) | Documentation ([Latest](https://www.dgl.ai/dgl_docs/) | [Official Examples](examples/README.md) | [Discussion Forum](https://discuss.dgl.ai) | [Slack Channel](https://join.slack.com/t/deep-graph-library/shared_invite/zt-eb4ict1g-xcg3PhZAFAB8p6dtKuP6xQ)
-DGL is an easy-to-use, high performance and scalable Python package for deep learning on graphs. DGL is framework agnostic, meaning if a deep graph model is a component of an end-to-end application, the rest of the logics can be implemented in any major frameworks, such as PyTorch, Apache MXNet or TensorFlow.
+DGL 是一个易用、高性能且可扩展的 Python 图深度学习（deep learning on graphs）包。DGL 与框架无关（framework agnostic），这意味着若深度图模型是端到端应用的一个组件，其余逻辑可在任意主流框架中实现，例如 PyTorch、Apache MXNet 或 TensorFlow。
- Figure: DGL Overall Architecture
+ Figure: DGL 整体架构
-## Highlighted Features
+## 亮点特性
-### A GPU-ready graph library
+### 面向 GPU 的图库
-DGL provides a powerful graph object that can reside on either CPU or GPU. It bundles structural data as well as features for better control. We provide a variety of functions for computing with graph objects including efficient and customizable message passing primitives for Graph Neural Networks.
+DGL 提供强大的图对象，可驻留在 CPU 或 GPU 上。它将结构数据与特征打包在一起，以便更好地控制。我们提供多种与图对象协同计算的函数，包括用于图神经网络（Graph Neural Networks）的高效且可定制的消息传递原语。
-### A versatile tool for GNN researchers and practitioners
+### 面向 GNN 研究者与实践者的多功能工具
-The field of graph deep learning is still rapidly evolving and many research ideas emerge by standing on the shoulders of giants. To ease the process, [DGl-Go](https://github.com/dmlc/dgl/tree/master/dglgo) is a command-line interface to get started with training, using and studying state-of-the-art GNNs.
-DGL collects a rich set of [example implementations](https://github.com/dmlc/dgl/tree/master/examples) of popular GNN models of a wide range of topics. Researchers can [search](https://www.dgl.ai/) for related models to innovate new ideas from or use them as baselines for experiments. Moreover, DGL provides many state-of-the-art [GNN layers and modules](https://docs.dgl.ai/api/python/nn.html) for users to build new model architectures. DGL is one of the preferred platforms for many standard graph deep learning benchmarks including [OGB](https://ogb.stanford.edu/) and [GNNBenchmarks](https://github.com/graphdeeplearning/benchmarking-gnns).
+图深度学习领域仍在快速发展，许多研究想法都建立在前人成果之上。为简化这一过程，[DGl-Go](https://github.com/dmlc/dgl/tree/master/dglgo) 是一个命令行界面，可用于入门训练、使用和研究最先进的 GNN。
+DGL 收集了大量涵盖广泛主题的流行 GNN 模型[示例实现](https://github.com/dmlc/dgl/tree/master/examples)。研究者可以[搜索](https://www.dgl.ai/)相关模型以创新新思路，或将其用作实验基线。此外，DGL 提供许多最先进的 [GNN 层与模块](https://docs.dgl.ai/api/python/nn.html)，供用户构建新的模型架构。DGL 是许多标准图深度学习基准的首选平台之一，包括 [OGB](https://ogb.stanford.edu/) 和 [GNNBenchmarks](https://github.com/graphdeeplearning/benchmarking-gnns).。
-### Easy to learn and use
+### 易学易用
-DGL provides plenty of learning materials for all kinds of users from ML researchers to domain experts. The [Blitz Introduction to DGL](https://docs.dgl.ai/tutorials/blitz/index.html) is a 120-minute tour of the basics of graph machine learning. The [User Guide](https://docs.dgl.ai/guide/index.html) explains in more details the concepts of graphs as well as the training methodology. All of them include code snippets in DGL that are runnable and ready to be plugged into one’s own pipeline.
+DGL 为从机器学习研究者到领域专家等各类用户提供丰富的学习材料。[Blitz Introduction to DGL](https://docs.dgl.ai/tutorials/blitz/index.html) 是对图机器学习基础知识的 120 分钟速览。[User Guide](https://docs.dgl.ai/guide/index.html) 更详细地解释了图的概念以及训练方法论。这些材料均包含 DGL 代码片段，可直接运行并接入用户自己的流水线。
-### Scalable and efficient
+### 可扩展且高效
-It is convenient to train models using DGL on large-scale graphs across **multiple GPUs** or **multiple machines**. DGL extensively optimizes the whole stack to reduce the overhead in communication, memory consumption and synchronization. As a result, DGL can easily scale to billion-sized graphs. Get started with the [tutorials](https://docs.dgl.ai/en/tutorials/dist/index.html) and [user guide](https://docs.dgl.ai/en/latest/guide/distributed.html) for distributed training. See the [system performance note](https://docs.dgl.ai/performance.html) for the comparison with other tools.
+使用 DGL 在**多 GPU**或**多机**环境下对大规模图进行模型训练十分便捷。DGL 对整个技术栈进行了广泛优化，以降低通信、内存占用和同步方面的开销。因此，DGL 可轻松扩展至十亿级规模的图。请从[教程](https://docs.dgl.ai/en/tutorials/dist/index.html)和[用户指南](https://docs.dgl.ai/en/latest/guide/distributed.html)入手分布式训练。请参阅[系统性能说明](https://docs.dgl.ai/performance.html)了解与其他工具的对比。
-## Get Started
+## 快速入门
-Users can install DGL from [pip and conda](https://www.dgl.ai/pages/start.html). You can also download GPU enabled DGL docker [containers](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/dgl) (backended by PyTorch) from NVIDIA NGC for both x86 and ARM based linux systems. Advanced users can follow the [instructions](https://docs.dgl.ai/install/index.html#install-from-source) to install from source.
+用户可通过 [pip 和 conda](https://www.dgl.ai/pages/start.html). 安装 DGL。也可从 NVIDIA NGC 下载支持 GPU 的 DGL Docker [容器](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/dgl)（基于 PyTorch 后端），适用于 x86 和 ARM 架构的 Linux 系统。高级用户可按照[说明](https://docs.dgl.ai/install/index.html#install-from-source)从源码安装。
-For absolute beginners, start with [the Blitz Introduction to DGL](https://docs.dgl.ai/tutorials/blitz/index.html). It covers the basic concepts of common graph machine learning tasks and a step-by-step on building Graph Neural Networks (GNNs) to solve them.
+对于零基础初学者，请从 [the Blitz Introduction to DGL](https://docs.dgl.ai/tutorials/blitz/index.html). 开始。它涵盖常见图机器学习任务的基本概念，以及分步构建图神经网络（GNN）以解决这些任务的流程。
-For acquainted users who wish to learn more,
+对于希望深入学习的有一定基础的用户，
-* Experience state-of-the-art GNN models in only two command-lines using [DGL-Go](https://github.com/dmlc/dgl/tree/master/dglgo).
-* Learn DGL by [example implementations](https://www.dgl.ai/) of popular GNN models.
-* Read the [User Guide](https://docs.dgl.ai/guide/index.html) ([中文版链接](https://docs.dgl.ai/guide_cn/index.html)), which explains the concepts and usage of DGL in much more details.
-* Go through the tutorials for advanced features like [stochastic training of GNNs](https://docs.dgl.ai/tutorials/large/index.html), training on [multi-GPU](https://docs.dgl.ai/tutorials/multi/index.html) or [multi-machine](https://docs.dgl.ai/tutorials/dist/index.html).
-* [Study classical papers](https://docs.dgl.ai/tutorials/models/index.html) on graph machine learning alongside DGL.
-* Search for the usage of a specific API in the [API reference manual](https://docs.dgl.ai/api/python/index.html), which organizes all DGL APIs by their namespace.
+* 使用 [DGL-Go](https://github.com/dmlc/dgl/tree/master/dglgo).，仅用两条命令行即可体验最先进的 GNN 模型
+* 通过流行 GNN 模型的[示例实现](https://www.dgl.ai/)学习 DGL。
+* 阅读 [User Guide](https://docs.dgl.ai/guide/index.html)（[中文版链接](https://docs.dgl.ai/guide_cn/index.html)),），其中更详细地解释了 DGL 的概念与用法。
+* 学习高级特性相关教程，例如 [GNN 随机训练](https://docs.dgl.ai/tutorials/large/index.html),、[多 GPU](https://docs.dgl.ai/tutorials/multi/index.html) 或[多机](https://docs.dgl.ai/tutorials/dist/index.html).训练。
+* 结合 DGL [研读图机器学习经典论文](https://docs.dgl.ai/tutorials/models/index.html)。
+* 在 [API 参考手册](https://docs.dgl.ai/api/python/index.html),中按命名空间查找特定 API 的用法。
-All the learning materials are available at our [documentation site](https://docs.dgl.ai/). If you are new to deep learning in general,
-check out the open source book [Dive into Deep Learning](https://d2l.ai/).
+所有学习材料均可在我们的[文档站点](https://docs.dgl.ai/).获取。若你刚接触深度学习，
+可参阅开源书籍 [Dive into Deep Learning](https://d2l.ai/).
-## Community
+## 社区
-### Get connected
+### 建立联系
-We provide multiple channels to connect you to the community of the DGL developers, users, and the general GNN academic researchers:
+我们提供多种渠道，将你与 DGL 开发者、用户以及更广泛的 GNN 学术研究者社区连接起来：
-* Our Slack channel, [click to join](https://join.slack.com/t/deep-graph-library/shared_invite/zt-eb4ict1g-xcg3PhZAFAB8p6dtKuP6xQ)
-* Our discussion forum: https://discuss.dgl.ai/
-* Our [Zhihu blog (in Chinese)](https://www.zhihu.com/column/c_1070749881013936128)
-* Monthly GNN User Group online seminar ([event link](https://www.eventbrite.com/e/graph-neural-networks-user-group-tickets-137512275919?utm-medium=discovery&utm-campaign=social&utm-content=attendeeshare&aff=escb&utm-source=cp&utm-term=listing) | [past videos](https://www.youtube.com/channel/UCnmuSDY1pTlaFH1WRQElfTg))
+* 我们的 Slack 频道，[点击加入](https://join.slack.com/t/deep-graph-library/shared_invite/zt-eb4ict1g-xcg3PhZAFAB8p6dtKuP6xQ)
+* 我们的讨论论坛：https://discuss.dgl.ai/
+* 我们的[知乎博客（中文）](https://www.zhihu.com/column/c_1070749881013936128)
+* 月度 GNN 用户组线上研讨会（[活动链接](https://www.eventbrite.com/e/graph-neural-networks-user-group-tickets-137512275919?utm-medium=discovery&utm-campaign=social&utm-content=attendeeshare&aff=escb&utm-source=cp&utm-term=listing) | [往期视频](https://www.youtube.com/channel/UCnmuSDY1pTlaFH1WRQElfTg))
-Take the survey [here](https://forms.gle/Ej3jHCocACmb49Gp8) and leave any feedback to make DGL better fit for your needs. Thanks!
+请[在此](https://forms.gle/Ej3jHCocACmb49Gp8)参与调查并留下反馈，帮助 DGL 更好地满足你的需求。感谢！
-### DGL-powered projects
+### 基于 DGL 的项目
-* DGL-LifeSci: a DGL-based package for various applications in life science with graph neural networks. https://github.com/awslabs/dgl-lifesci
-* DGL-KE: a high performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings. https://github.com/awslabs/dgl-ke
-* Benchmarking GNN: https://github.com/graphdeeplearning/benchmarking-gnns
-* OGB: a collection of realistic, large-scale, and diverse benchmark datasets for machine learning on graphs. https://ogb.stanford.edu/
-* Graph4NLP: an easy-to-use library for R&D at the intersection of Deep Learning on Graphs and Natural Language Processing. https://github.com/graph4ai/graph4nlp
-* GNN-RecSys: https://github.com/je-dbl/GNN-RecSys
-* Amazon Neptune ML: a new capability of Neptune that uses Graph Neural Networks (GNNs), a machine learning technique purpose-built for graphs, to make easy, fast, and more accurate predictions using graph data. https://aws.amazon.com/cn/neptune/machine-learning/
-* GNNLens2: Visualization tool for Graph Neural Networks. https://github.com/dmlc/GNNLens2
-* RNAGlib: A package to facilitate construction, analysis, visualization and machine learning on RNA 2.5D Graphs. Includes a pre-built dataset: https://rnaglib.cs.mcgill.ca
-* OpenHGNN: Model zoo and benchmarks for Heterogeneous Graph Neural Networks. https://github.com/BUPT-GAMMA/OpenHGNN
-* TGL: A graph learning framework for large-scale temporal graphs. https://github.com/amazon-research/tgl
-* gtrick: Bag of Tricks for Graph Neural Networks. https://github.com/sangyx/gtrick
-* ArangoDB-DGL Adapter: Import [ArangoDB](https://github.com/arangodb/arangodb) graphs into DGL and vice-versa. https://github.com/arangoml/dgl-adapter
-* DGLD: [DGLD](https://github.com/EagleLab-ZJU/DGLD) is an open-source library for Deep Graph Anomaly Detection based on pytorch and DGL.
-### Awesome Papers Using DGL
+* DGL-LifeSci：基于 DGL 的软件包，用于生命科学领域各类图神经网络应用。https://github.com/awslabs/dgl-lifesci
+* DGL-KE：用于学习大规模知识图谱嵌入的高性能、易用且可扩展的软件包。https://github.com/awslabs/dgl-ke
+* Benchmarking GNN：https://github.com/graphdeeplearning/benchmarking-gnns
+* OGB：面向图机器学习的一组真实、大规模且多样化的基准数据集。https://ogb.stanford.edu/
+* Graph4NLP：面向图深度学习与自然语言处理交叉领域研发（R&D）的易用库。https://github.com/graph4ai/graph4nlp
+* GNN-RecSys：https://github.com/je-dbl/GNN-RecSys
+* Amazon Neptune ML：Neptune 的一项新能力，使用专为图设计的机器学习技术——图神经网络（GNNs）——以便利用图数据做出更轻松、更快速且更准确的预测。https://aws.amazon.com/cn/neptune/machine-learning/
+* GNNLens2：图神经网络可视化工具。https://github.com/dmlc/GNNLens2
+* RNAGlib：便于在 RNA 2.5D 图上进行构建、分析、可视化与机器学习的软件包。包含预构建数据集：https://rnaglib.cs.mcgill.ca
+* OpenHGNN：异构图神经网络（Heterogeneous Graph Neural Networks）的模型库与基准。https://github.com/BUPT-GAMMA/OpenHGNN
+* TGL：面向大规模时序图的图学习框架。https://github.com/amazon-research/tgl
+* gtrick：图神经网络的技巧合集（Bag of Tricks）。https://github.com/sangyx/gtrick
+* ArangoDB-DGL Adapter：将 [ArangoDB](https://github.com/arangodb/arangodb) 图导入 DGL，或反向导出。https://github.com/arangoml/dgl-adapter
+* DGLD：[DGLD](https://github.com/EagleLab-ZJU/DGLD) 是基于 PyTorch 和 DGL 的深度图异常检测开源库。
-1. [**Benchmarking Graph Neural Networks**](https://arxiv.org/pdf/2003.00982.pdf), *Vijay Prakash Dwivedi, Chaitanya K. Joshi, Thomas Laurent, Yoshua Bengio, Xavier Bresson*
+### 使用 DGL 的优秀论文
-1. [**Open Graph Benchmarks: Datasets for Machine Learning on Graphs**](https://arxiv.org/pdf/2005.00687.pdf), NeurIPS'20, *Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, Jure Leskovec*
+1. [**图神经网络基准测试（Benchmarking Graph Neural Networks）**](https://arxiv.org/pdf/2003.00982.pdf), *Vijay Prakash Dwivedi, Chaitanya K. Joshi, Thomas Laurent, Yoshua Bengio, Xavier Bresson*
-1. [**DropEdge: Towards Deep Graph Convolutional Networks on Node Classification**](https://openreview.net/pdf?id=Hkx1qkrKPr), ICLR'20, *Yu Rong, Wenbing Huang, Tingyang Xu, Junzhou Huan*
+1. [**开放图基准（Open Graph Benchmarks）：用于图上机器学习的数据集**](https://arxiv.org/pdf/2005.00687.pdf), NeurIPS'20, *Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, Jure Leskovec*
-1. [**Discourse-Aware Neural Extractive Text Summarization**](https://www.aclweb.org/anthology/2020.acl-main.451/), ACL'20, *Jiacheng Xu, Zhe Gan, Yu Cheng, Jingjing Liu*
+1. [**DropEdge：面向节点分类的深度图卷积网络**](https://openreview.net/pdf?id=Hkx1qkrKPr), ICLR'20, *Yu Rong, Wenbing Huang, Tingyang Xu, Junzhou Huan*
-1. [**GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training**](https://dl.acm.org/doi/pdf/10.1145/3394486.3403168?casa_token=EClsH2Vc4DcAAAAA:LIB8cbtr6yTDbYuv4cTLwTIYeDq5Y2dhj_ktcWdKpzdPLGeiuL0o8GlcN4QIOnpsAnmGeGVZ), KDD'20, *Jiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang, Hongxia Yang, Ming Ding, Kuansan Wang, Jie Tang*
+1. [**话语感知的神经抽取式文本摘要**](https://www.aclweb.org/anthology/2020.acl-main.451/), ACL'20, *Jiacheng Xu, Zhe Gan, Yu Cheng, Jingjing Liu*
-1. [**DGL-KE: Training Knowledge Graph Embeddings at Scale**](https://arxiv.org/pdf/2004.08532), SIGIR'20, *Da Zheng, Xiang Song, Chao Ma, Zeyuan Tan, Zihao Ye, Jin Dong, Hao Xiong, Zheng Zhang, George Karypis*
+1. [**GCC：用于图神经网络预训练的图对比编码**](https://dl.acm.org/doi/pdf/10.1145/3394486.3403168?casa_token=EClsH2Vc4DcAAAAA:LIB8cbtr6yTDbYuv4cTLwTIYeDq5Y2dhj_ktcWdKpzdPLGeiuL0o8GlcN4QIOnpsAnmGeGVZ), KDD'20, *Jiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang, Hongxia Yang, Ming Ding, Kuansan Wang, Jie Tang*
-1. [**Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting**](https://arxiv.org/pdf/2006.09252.pdf), *Giorgos Bouritsas, Fabrizio Frasca, Stefanos Zafeiriou, Michael M. Bronstein*
+1. [**DGL-KE：大规模训练知识图谱嵌入**](https://arxiv.org/pdf/2004.08532), SIGIR'20, *Da Zheng, Xiang Song, Chao Ma, Zeyuan Tan, Zihao Ye, Jin Dong, Hao Xiong, Zheng Zhang, George Karypis*
-1. [**INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving**](https://arxiv.org/pdf/2007.02924.pdf), *Yuhuai Wu, Albert Q. Jiang, Jimmy Ba, Roger Grosse*
+1. [**通过子图同构计数提升图神经网络表达能力**](https://arxiv.org/pdf/2006.09252.pdf), *Giorgos Bouritsas, Fabrizio Frasca, Stefanos Zafeiriou, Michael M. Bronstein*
-1. [**Finding Patient Zero: Learning Contagion Source with Graph Neural Networks**](https://arxiv.org/pdf/2006.11913.pdf), *Chintan Shah, Nima Dehmamy, Nicola Perra, Matteo Chinazzi, Albert-László Barabási, Alessandro Vespignani, Rose Yu*
+1. [**INT：用于评估定理证明泛化能力的不等式基准**](https://arxiv.org/pdf/2007.02924.pdf), *Yuhuai Wu, Albert Q. Jiang, Jimmy Ba, Roger Grosse*
-1. [**FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems**](https://arxiv.org/pdf/2008.11359.pdf), SC'20, *Yuwei Hu, Zihao Ye, Minjie Wang, Jiali Yu, Da Zheng, Mu Li, Zheng Zhang, Zhiru Zhang, Yida Wang*
+1. [**寻找零号病人：使用图神经网络学习传染源**](https://arxiv.org/pdf/2006.11913.pdf), *Chintan Shah, Nima Dehmamy, Nicola Perra, Matteo Chinazzi, Albert-László Barabási, Alessandro Vespignani, Rose Yu*
+1. [**FeatGraph：灵活高效的图神经网络系统后端**](https://arxiv.org/pdf/2008.11359.pdf), SC'20, *Yuwei Hu, Zihao Ye, Minjie Wang, Jiali Yu, Da Zheng, Mu Li, Zheng Zhang, Zhiru Zhang, Yida Wang*
-more
-11. [**BP-Transformer: Modelling Long-Range Context via Binary Partitioning.**](https://arxiv.org/pdf/1911.04070.pdf), *Zihao Ye, Qipeng Guo, Quan Gan, Xipeng Qiu, Zheng Zhang*
+更多
-12. [**OptiMol: Optimization of Binding Affinities in Chemical Space for Drug Discovery**](https://www.biorxiv.org/content/biorxiv/early/2020/06/16/2020.05.23.112201.full.pdf), *Jacques Boitreaud,Vincent Mallet, Carlos Oliver, Jérôme Waldispühl*
+11. [**BP-Transformer：通过二分划分建模长程上下文**](https://arxiv.org/pdf/1911.04070.pdf), *Zihao Ye, Qipeng Guo, Quan Gan, Xipeng Qiu, Zheng Zhang*
-1. [**JAKET: Joint Pre-training of Knowledge Graph and Language Understanding**](https://arxiv.org/pdf/2010.00796.pdf), *Donghan Yu, Chenguang Zhu, Yiming Yang, Michael Zeng*
+12. [**OptiMol：在化学空间中优化结合亲和力以用于药物发现**](https://www.biorxiv.org/content/biorxiv/early/2020/06/16/2020.05.23.112201.full.pdf), *Jacques Boitreaud,Vincent Mallet, Carlos Oliver, Jérôme Waldispühl*
-1. [**Architectural Implications of Graph Neural Networks**](https://arxiv.org/pdf/2009.00804.pdf), *Zhihui Zhang, Jingwen Leng, Lingxiao Ma, Youshan Miao, Chao Li, Minyi Guo*
+1. [**JAKET：知识图谱与语言理解的联合预训练**](https://arxiv.org/pdf/2010.00796.pdf), *Donghan Yu, Chenguang Zhu, Yiming Yang, Michael Zeng*
-1. [**Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization**](https://arxiv.org/pdf/2006.01610.pdf), *Quentin Cappart, Thierry Moisan, Louis-Martin Rousseau1, Isabeau Prémont-Schwarz, and Andre Cire*
+1. [**图神经网络的架构影响**](https://arxiv.org/pdf/2009.00804.pdf), *Zhihui Zhang, Jingwen Leng, Lingxiao Ma, Youshan Miao, Chao Li, Minyi Guo*
-1. [**Therapeutics Data Commons: Machine Learning Datasets and Tasks for Therapeutics**](https://arxiv.org/abs/2102.09548) ([code repo](https://github.com/mims-harvard/TDC)), *Kexin Huang, Tianfan Fu, Wenhao Gao, Yue Zhao, Yusuf Roohani, Jure Leskovec, Connor W. Coley, Cao Xiao, Jimeng Sun, Marinka Zitnik*
+1. [**结合强化学习与约束编程进行组合优化**](https://arxiv.org/pdf/2006.01610.pdf), *Quentin Cappart, Thierry Moisan, Louis-Martin Rousseau1, Isabeau Prémont-Schwarz, and Andre Cire*
-1. [**Sparse Graph Attention Networks**](https://arxiv.org/abs/1912.00552), *Yang Ye, Shihao Ji*
+1. [**治疗数据共享平台（Therapeutics Data Commons）：用于治疗领域的机器学习数据集与任务**](https://arxiv.org/abs/2102.09548) ([code repo](https://github.com/mims-harvard/TDC)), *Kexin Huang, Tianfan Fu, Wenhao Gao, Yue Zhao, Yusuf Roohani, Jure Leskovec, Connor W. Coley, Cao Xiao, Jimeng Sun, Marinka Zitnik*
-1. [**On Self-Distilling Graph Neural Network**](https://arxiv.org/pdf/2011.02255.pdf), *Yuzhao Chen, Yatao Bian, Xi Xiao, Yu Rong, Tingyang Xu, Junzhou Huang*
+1. [**稀疏图注意力网络**](https://arxiv.org/abs/1912.00552), *Yang Ye, Shihao Ji*
-1. [**Learning Robust Node Representations on Graphs**](https://arxiv.org/pdf/2008.11416.pdf), *Xu Chen, Ya Zhang, Ivor Tsang, and Yuangang Pan*
+1. [**论图神经网络的自蒸馏**](https://arxiv.org/pdf/2011.02255.pdf), *Yuzhao Chen, Yatao Bian, Xi Xiao, Yu Rong, Tingyang Xu, Junzhou Huang*
-1. [**Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs**](https://arxiv.org/abs/1904.05530), *Woojeong Jin, Meng Qu, Xisen Jin, Xiang Ren*
+1. [**学习图上的鲁棒节点表示**](https://arxiv.org/pdf/2008.11416.pdf), *Xu Chen, Ya Zhang, Ivor Tsang, and Yuangang Pan*
-1. [**Graph Neural Ordinary Differential Equations**](https://arxiv.org/abs/1911.07532), *Michael Poli, Stefano Massaroli, Junyoung Park, Atsushi Yamashita, Hajime Asama, Jinkyoo Park*
+1. [**循环事件网络（Recurrent Event Network）：时序知识图谱上的自回归结构推断**](https://arxiv.org/abs/1904.05530), *Woojeong Jin, Meng Qu, Xisen Jin, Xiang Ren*
-1. [**FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networks**](https://arxiv.org/pdf/2011.06391.pdf), *Md. Khaledur Rahman, Majedul Haque Sujon, , Ariful Azad*
+1. [**图神经常微分方程**](https://arxiv.org/abs/1911.07532), *Michael Poli, Stefano Massaroli, Junyoung Park, Atsushi Yamashita, Hajime Asama, Jinkyoo Park*
-1. [**An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph**](https://arxiv.org/pdf/2007.00216.pdf), KDD'20 *Jiarui Jin, Jiarui Qin, Yuchen Fang, Kounianhua Du, Weinan Zhang, Yong Yu, Zheng Zhang, Alexander J. Smola*
+1. [**FusedMM：面向图嵌入与图神经网络的统一 SDDMM-SpMM 内核**](https://arxiv.org/pdf/2011.06391.pdf), *Md. Khaledur Rahman, Majedul Haque Sujon, , Ariful Azad*
-1. [**Learning Interaction Models of Structured Neighborhood on Heterogeneous Information Network**](https://arxiv.org/pdf/2011.12683.pdf), *Jiarui Jin, Kounianhua Du, Weinan Zhang, Jiarui Qin, Yuchen Fang, Yong Yu, Zheng Zhang, Alexander J. Smola*
+1. [**异构图推荐的高效邻域交互模型**](https://arxiv.org/pdf/2007.00216.pdf), KDD'20 *Jiarui Jin, Jiarui Qin, Yuchen Fang, Kounianhua Du, Weinan Zhang, Yong Yu, Zheng Zhang, Alexander J. Smola*
-1. [**Graphein - a Python Library for Geometric Deep Learning and Network Analysis on Protein Structures**](https://www.biorxiv.org/content/10.1101/2020.07.15.204701v1), *Arian R. Jamasb, Pietro Lió, Tom L. Blundell*
+1. [**异构信息网上结构化邻域的交互模型学习**](https://arxiv.org/pdf/2011.12683.pdf), *Jiarui Jin, Kounianhua Du, Weinan Zhang, Jiarui Qin, Yuchen Fang, Yong Yu, Zheng Zhang, Alexander J. Smola*
-1. [**Graph Policy Gradients for Large Scale Robot Control**](https://arxiv.org/abs/1907.03822), *Arbaaz Khan, Ekaterina Tolstaya, Alejandro Ribeiro, Vijay Kumar*
+1. [**Graphein——用于蛋白质结构几何深度学习与网络分析的 Python 库**](https://www.biorxiv.org/content/10.1101/2020.07.15.204701v1), *Arian R. Jamasb, Pietro Lió, Tom L. Blundell*
-1. [**Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties**](https://arxiv.org/abs/2009.12710), *Zeren Shui, George Karypis*
+1. [**面向大规模机器人控制的图策略梯度**](https://arxiv.org/abs/1907.03822), *Arbaaz Khan, Ekaterina Tolstaya, Alejandro Ribeiro, Vijay Kumar*
-1. [**Could Graph Neural Networks Learn Better Molecular Representation for Drug Discovery? A Comparison Study of Descriptor-based and Graph-based Models**](https://assets.researchsquare.com/files/rs-81439/v1_stamped.pdf), *Dejun Jiang, Zhenxing Wu, Chang-Yu Hsieh, Guangyong Chen, Ben Liao, Zhe Wang, Chao Shen, Dongsheng Cao, Jian Wu, Tingjun Hou*
+1. [**用于预测分子性质的异构分子图神经网络**](https://arxiv.org/abs/2009.12710), *Zeren Shui, George Karypis*
-1. [**Principal Neighbourhood Aggregation for Graph Nets**](https://arxiv.org/abs/2004.05718), *Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò, Petar Veličković*
+1. [**图神经网络能否为药物发现学习更好的分子表示？基于描述符与基于图模型的对比研究**](https://assets.researchsquare.com/files/rs-81439/v1_stamped.pdf), *Dejun Jiang, Zhenxing Wu, Chang-Yu Hsieh, Guangyong Chen, Ben Liao, Zhe Wang, Chao Shen, Dongsheng Cao, Jian Wu, Tingjun Hou*
-1. [**Collective Multi-type Entity Alignment Between Knowledge Graphs**](https://dl.acm.org/doi/abs/10.1145/3366423.3380289), *Qi Zhu, Hao Wei, Bunyamin Sisman, Da Zheng, Christos Faloutsos, Xin Luna Dong, Jiawei Han*
+1. [**图网络的主邻域聚合（Principal Neighbourhood Aggregation）**](https://arxiv.org/abs/2004.05718), *Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò, Petar Veličković*
-1. [**Graph Representation Forecasting of Patient's Medical Conditions: towards A Digital Twin**](https://arxiv.org/abs/2009.08299), *Pietro Barbiero, Ramon Viñas Torné, Pietro Lió*
+1. [**知识图谱间的集体多类型实体对齐**](https://dl.acm.org/doi/abs/10.1145/3366423.3380289), *Qi Zhu, Hao Wei, Bunyamin Sisman, Da Zheng, Christos Faloutsos, Xin Luna Dong, Jiawei Han*
-1. [**Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgery**](https://arxiv.org/abs/2011.01619), *Yong-Hao Long, Jie-Ying Wu, Bo Lu, Yue-Ming Jin, Mathias Unberath, Yun-Hui Liu, Pheng-Ann Heng and Qi Dou*
+1. [**患者医疗状况的图表示预测：迈向数字孪生**](https://arxiv.org/abs/2009.08299), *Pietro Barbiero, Ramon Viñas Torné, Pietro Lió*
-1. [**Dark Reciprocal-Rank: Boosting Graph-Convolutional Self-Localization Network via Teacher-to-student Knowledge Transfer**](https://arxiv.org/abs/2011.00402), *Takeda Koji, Tanaka Kanji*
+1. [**基于视觉与运动学嵌入的关系图学习用于机器人手术中的精准手势识别**](https://arxiv.org/abs/2011.01619), *Yong-Hao Long, Jie-Ying Wu, Bo Lu, Yue-Ming Jin, Mathias Unberath, Yun-Hui Liu, Pheng-Ann Heng and Qi Dou*
-1. [**Graph InfoClust: Leveraging Cluster-Level Node Information For Unsupervised Graph Representation Learning**](https://arxiv.org/abs/2009.06946), *Costas Mavromatis, George Karypis*
+1. [**Dark Reciprocal-Rank：通过师生知识迁移增强图卷积自定位网络**](https://arxiv.org/abs/2011.00402), *Takeda Koji, Tanaka Kanji*
-1. [**GraphSeam: Supervised Graph Learning Framework for Semantic UV Mapping**](https://arxiv.org/abs/2011.13748), *Fatemeh Teimury, Bruno Roy, Juan Sebastian Casallas, David macdonald, Mark Coates*
+1. [**Graph InfoClust：利用簇级节点信息进行无监督图表示学习**](https://arxiv.org/abs/2009.06946), *Costas Mavromatis, George Karypis*
-1. [**Comprehensive Study on Molecular Supervised Learning with Graph Neural Networks**](https://pubs.acs.org/doi/10.1021/acs.jcim.0c00416), *Doyeong Hwang, Soojung Yang, Yongchan Kwon, Kyung Hoon Lee, Grace Lee, Hanseok Jo, Seyeol Yoon, and Seongok Ryu*
+1. [**GraphSeam：用于语义 UV 映射的监督图学习框架**](https://arxiv.org/abs/2011.13748), *Fatemeh Teimury, Bruno Roy, Juan Sebastian Casallas, David macdonald, Mark Coates*
-1. [**A graph auto-encoder model for miRNA-disease associations prediction**](https://academic.oup.com/bib/advance-article-abstract/doi/10.1093/bib/bbaa240/5929824?redirectedFrom=fulltext), *Zhengwei Li, Jiashu Li, Ru Nie, Zhu-Hong You, Wenzheng Bao*
+1. [**基于图神经网络的分子监督学习综合研究**](https://pubs.acs.org/doi/10.1021/acs.jcim.0c00416), *Doyeong Hwang, Soojung Yang, Yongchan Kwon, Kyung Hoon Lee, Grace Lee, Hanseok Jo, Seyeol Yoon, and Seongok Ryu*
-1. [**Graph convolutional regression of cardiac depolarization from sparse endocardial maps**](https://arxiv.org/abs/2009.14068), STACOM 2020 workshop, *Felix Meister, Tiziano Passerini, Chloé Audigier, Èric Lluch, Viorel Mihalef, Hiroshi Ashikaga, Andreas Maier, Henry Halperin, Tommaso Mansi*
+1. [**用于 miRNA-疾病关联预测的图自编码器模型**](https://academic.oup.com/bib/advance-article-abstract/doi/10.1093/bib/bbaa240/5929824?redirectedFrom=fulltext), *Zhengwei Li, Jiashu Li, Ru Nie, Zhu-Hong You, Wenzheng Bao*
-1. [**AttnIO: Knowledge Graph Exploration with In-and-Out Attention Flow for Knowledge-Grounded Dialogue**](https://www.aclweb.org/anthology/2020.emnlp-main.280/), EMNLP'20, *Jaehun Jung, Bokyung Son, Sungwon Lyu*
+1. [**从稀疏心内膜图谱进行心脏去极化的图卷积回归**](https://arxiv.org/abs/2009.14068), STACOM 2020 workshop, *Felix Meister, Tiziano Passerini, Chloé Audigier, Èric Lluch, Viorel Mihalef, Hiroshi Ashikaga, Andreas Maier, Henry Halperin, Tommaso Mansi*
-1. [**Learning from Non-Binary Constituency Trees via Tensor Decomposition**](https://github.com/danielecastellana22/tensor-tree-nn), COLING'20, *Daniele Castellana, Davide Bacciu*
+1. [**AttnIO：面向知识落地对话的进出注意力流知识图谱探索**](https://www.aclweb.org/anthology/2020.emnlp-main.280/), EMNLP'20, *Jaehun Jung, Bokyung Son, Sungwon Lyu*
-1. [**Inducing Alignment Structure with Gated Graph Attention Networks for Sentence Matching**](https://arxiv.org/abs/2010.07668), *Peng Cui, Le Hu, Yuanchao Liu*
+1. [**通过张量分解从非二元成分树中学习**](https://github.com/danielecastellana22/tensor-tree-nn), COLING'20, *Daniele Castellana, Davide Bacciu*
-1. [**Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks**](https://arxiv.org/abs/2010.06253), COLING'20, *Peng Cui, Le Hu, Yuanchao Liu*
+1. [**利用门控图注意力网络诱导对齐结构用于句子匹配**](https://arxiv.org/abs/2010.07668), *Peng Cui, Le Hu, Yuanchao Liu*
-1. [**Double Graph Based Reasoning for Document-level Relation Extraction**](https://arxiv.org/abs/2009.13752), EMNLP'20, *Shuang Zeng, Runxin Xu, Baobao Chang, Lei Li*
+1. [**利用主题感知图神经网络增强抽取式文本摘要**](https://arxiv.org/abs/2010.06253), COLING'20, *Peng Cui, Le Hu, Yuanchao Liu*
-1. [**Systematic Generalization on gSCAN with Language Conditioned Embedding**](https://arxiv.org/abs/2009.05552), AACL-IJCNLP'20, *Tong Gao, Qi Huang, Raymond J. Mooney*
+1. [**基于双图的文档级关系抽取推理**](https://arxiv.org/abs/2009.13752), EMNLP'20, *Shuang Zeng, Runxin Xu, Baobao Chang, Lei Li*
-1. [**Automatic selection of clustering algorithms using supervised graph embedding**](https://arxiv.org/pdf/2011.08225.pdf), *Noy Cohen-Shapira, Lior Rokach*
+1. [**基于语言条件嵌入在 gSCAN 上的系统化泛化**](https://arxiv.org/abs/2009.05552), AACL-IJCNLP'20, *Tong Gao, Qi Huang, Raymond J. Mooney*
-1. [**Improving Learning to Branch via Reinforcement Learning**](https://openreview.net/forum?id=z4D7-PTxTb), *Haoran Sun, Wenbo Chen, Hui Li, Le Song*
+1. [**利用监督图嵌入自动选择聚类算法**](https://arxiv.org/pdf/2011.08225.pdf), *Noy Cohen-Shapira, Lior Rokach*
-1. [**A Practical Guide to Graph Neural Networks**](https://arxiv.org/pdf/2010.05234.pdf), *Isaac Ronald Ward, Jack Joyner, Casey Lickfold, Stash Rowe, Yulan Guo, Mohammed Bennamoun*, [code](https://github.com/isolabs/gnn-tutorial)
+1. [**通过强化学习改进学习分支**](https://openreview.net/forum?id=z4D7-PTxTb), *Haoran Sun, Wenbo Chen, Hui Li, Le Song*
-1. [**APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding**](https://arxiv.org/pdf/2011.11545.pdf), SIGMOD'21, *Xuhong Wang, Ding Lyu, Mengjian Li, Yang Xia, Qi Yang, Xinwen Wang, Xinguang Wang, Ping Cui, Yupu Yang, Bowen Sun, Zhenyu Guo, Junkui Li*
+1. [**图神经网络实用指南**](https://arxiv.org/pdf/2010.05234.pdf), *Isaac Ronald Ward, Jack Joyner, Casey Lickfold, Stash Rowe, Yulan Guo, Mohammed Bennamoun*, [代码](https://github.com/isolabs/gnn-tutorial)
-1. [**Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks**](https://arxiv.org/pdf/2009.14455.pdf), *Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Andreas Spanias*
+1. [**APAN：用于实时时序图嵌入的异步传播注意力网络**](https://arxiv.org/pdf/2011.11545.pdf), SIGMOD'21, *Xuhong Wang, Ding Lyu, Mengjian Li, Yang Xia, Qi Yang, Xinwen Wang, Xinguang Wang, Ping Cui, Yupu Yang, Bowen Sun, Zhenyu Guo, Junkui Li*
-1. [**Computing Graph Neural Networks: A Survey from Algorithms to Accelerators**](https://arxiv.org/pdf/2010.00130.pdf), *Sergi Abadal, Akshay Jain, Robert Guirado, Jorge López-Alonso, Eduard Alarcón*
+1. [**不确定性匹配图神经网络防御投毒攻击**](https://arxiv.org/pdf/2009.14455.pdf), *Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Andreas Spanias*
-1. [**NHK_STRL at WNUT-2020 Task 2: GATs with Syntactic Dependencies as Edges and CTC-based Loss for Text Classification**](https://www.aclweb.org/anthology/2020.wnut-1.43.pdf), *Yuki Yasuda, Taichi Ishiwatari, Taro Miyazaki, Jun Goto*
+1. [**图神经网络计算：从算法到加速器的综述**](https://arxiv.org/pdf/2010.00130.pdf), *Sergi Abadal, Akshay Jain, Robert Guirado, Jorge López-Alonso, Eduard Alarcón*
-1. [**Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations**](https://www.aclweb.org/anthology/2020.emnlp-main.597.pdf), *Taichi Ishiwatari, Yuki Yasuda, Taro Miyazaki, Jun Goto*
+1. [**NHK_STRL 在 WNUT-2020 任务 2：以句法依存为边的 GAT 与基于 CTC 的文本分类损失**](https://www.aclweb.org/anthology/2020.wnut-1.43.pdf), *Yuki Yasuda, Taichi Ishiwatari, Taro Miyazaki, Jun Goto*
-1. [**PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks**](https://proceedings.neurips.cc/paper/2020/file/8fb134f258b1f7865a6ab2d935a897c9-Paper.pdf), *Minh N. Vu, My T. Thai*
+1. [**面向对话情感识别的关系感知图注意力网络与关系位置编码**](https://www.aclweb.org/anthology/2020.emnlp-main.597.pdf), *Taichi Ishiwatari, Yuki Yasuda, Taro Miyazaki, Jun Goto*
-1. [**A Generalization of Transformer Networks to Graphs**](https://arxiv.org/pdf/2012.09699.pdf), *Vijay Prakash Dwivedi, Xavier Bresson*
+1. [**PGM-Explainer：图神经网络的概率图模型解释**](https://proceedings.neurips.cc/paper/2020/file/8fb134f258b1f7865a6ab2d935a897c9-Paper.pdf), *Minh N. Vu, My T. Thai*
-1. [**Discourse-Aware Neural Extractive Text Summarization**](https://www.aclweb.org/anthology/2020.acl-main.451.pdf), ACL'20, *Jiacheng Xu, Zhe Gan, Yu Cheng, Jingjing Liu*
+1. [**Transformer 网络在图上的推广**](https://arxiv.org/pdf/2012.09699.pdf), *Vijay Prakash Dwivedi, Xavier Bresson*
-1. [**Learning Robust Node Representations on Graphs**](https://arxiv.org/abs/2008.11416), *Xu Chen, Ya Zhang, Ivor Tsang, Yuangang Pan*
+1. [**话语感知的神经抽取式文本摘要**](https://www.aclweb.org/anthology/2020.acl-main.451.pdf), ACL'20, *Jiacheng Xu, Zhe Gan, Yu Cheng, Jingjing Liu*
-1. [**Adaptive Graph Diffusion Networks with Hop-wise Attention**](https://arxiv.org/abs/2012.15024), *Chuxiong Sun, Guoshi Wu*
+1. [**在图上学得鲁棒节点表示**](https://arxiv.org/abs/2008.11416), *Xu Chen, Ya Zhang, Ivor Tsang, Yuangang Pan*
-1. [**The Photoswitch Dataset: A Molecular Machine Learning Benchmark for the Advancement of Synthetic Chemistry**](https://arxiv.org/abs/2008.03226), *Aditya R. Thawani, Ryan-Rhys Griffiths, Arian Jamasb, Anthony Bourached, Penelope Jones, William McCorkindale, Alexander A. Aldrick, Alpha A. Lee*
+1. [**带逐跳注意力的自适应图扩散网络**](https://arxiv.org/abs/2012.15024), *Chuxiong Sun, Guoshi Wu*
-1. [**A community-powered search of machine learning strategy space to find NMR property prediction models**](https://arxiv.org/abs/2008.05994), *Lars A. Bratholm, Will Gerrard, Brandon Anderson, Shaojie Bai, Sunghwan Choi, Lam Dang, Pavel Hanchar, Addison Howard, Guillaume Huard, Sanghoon Kim, Zico Kolter, Risi Kondor, Mordechai Kornbluth, Youhan Lee, Youngsoo Lee, Jonathan P. Mailoa, Thanh Tu Nguyen, Milos Popovic, Goran Rakocevic, Walter Reade, Wonho Song, Luka Stojanovic, Erik H. Thiede, Nebojsa Tijanic, Andres Torrubia, Devin Willmott, Craig P. Butts, David R. Glowacki, Kaggle participants*
+1. [**Photoswitch 数据集：推动合成化学发展的分子机器学习基准**](https://arxiv.org/abs/2008.03226), *Aditya R. Thawani, Ryan-Rhys Griffiths, Arian Jamasb, Anthony Bourached, Penelope Jones, William McCorkindale, Alexander A. Aldrick, Alpha A. Lee*
-1. [**Adaptive Layout Decomposition with Graph Embedding Neural Networks**](http://www.cse.cuhk.edu.hk/~byu/papers/C98-DAC2020-MPL-Selector.pdf), *Wei Li, Jialu Xia, Yuzhe Ma, Jialu Li, Yibo Lin, Bei Yu*, DAC'20
+1. [**社区驱动的机器学习策略空间搜索以发现 NMR 性质预测模型**](https://arxiv.org/abs/2008.05994), *Lars A. Bratholm, Will Gerrard, Brandon Anderson, Shaojie Bai, Sunghwan Choi, Lam Dang, Pavel Hanchar, Addison Howard, Guillaume Huard, Sanghoon Kim, Zico Kolter, Risi Kondor, Mordechai Kornbluth, Youhan Lee, Youngsoo Lee, Jonathan P. Mailoa, Thanh Tu Nguyen, Milos Popovic, Goran Rakocevic, Walter Reade, Wonho Song, Luka Stojanovic, Erik H. Thiede, Nebojsa Tijanic, Andres Torrubia, Devin Willmott, Craig P. Butts, David R. Glowacki, Kaggle participants*
-1. [**Transfer Learning with Graph Neural Networks for Optoelectronic Properties of Conjugated Oligomers**](https://aip.scitation.org/doi/10.1063/5.0037863), J. Chem. Phys. 154, *Chee-Kong Lee, Chengqiang Lu, Yue Yu, Qiming Sun, Chang-Yu Hsieh, Shengyu Zhang, Qi Liu, and Liang Shi*
+1. [**基于图嵌入神经网络的自适应版图分解**](http://www.cse.cuhk.edu.hk/~byu/papers/C98-DAC2020-MPL-Selector.pdf), *Wei Li, Jialu Xia, Yuzhe Ma, Jialu Li, Yibo Lin, Bei Yu*, DAC'20
-1. [**Jet tagging in the Lund plane with graph networks**](https://link.springer.com/article/10.1007/JHEP03(2021)052), Journal of High Energy Physics 2021, *Frédéric A. Dreyer and Huilin Qu*
+1. [**利用图神经网络迁移学习预测共轭寡聚物的光电性质**](https://aip.scitation.org/doi/10.1063/5.0037863), J. Chem. Phys. 154, *Chee-Kong Lee, Chengqiang Lu, Yue Yu, Qiming Sun, Chang-Yu Hsieh, Shengyu Zhang, Qi Liu, and Liang Shi*
-1. [**Global Attention Improves Graph Networks Generalization**](https://arxiv.org/abs/2006.07846), *Omri Puny, Heli Ben-Hamu, and Yaron Lipman*
+1. [**在 Lund 平面利用图网络进行喷注标记**](https://link.springer.com/article/10.1007/JHEP03(2021)052), Journal of High Energy Physics 2021, *Frédéric A. Dreyer and Huilin Qu*
-1. [**Learning over Families of Sets -- Hypergraph Representation Learning for Higher Order Tasks**](https://arxiv.org/abs/2101.07773), SDM 2021, *Balasubramaniam Srinivasan, Da Zheng, and George Karypis*
+1. [**全局注意力提升图网络泛化能力**](https://arxiv.org/abs/2006.07846), *Omri Puny, Heli Ben-Hamu, and Yaron Lipman*
-1. [**SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolution Networks**](https://arxiv.org/abs/2102.10338), *Haimin Zhang, Min Xu*
+1. [**在集合族上学习——面向高阶任务的超图表示学习**](https://arxiv.org/abs/2101.07773), SDM 2021, *Balasubramaniam Srinivasan, Da Zheng, and George Karypis*
-1. [**Application and evaluation of knowledge graph embeddings in biomedical data**](https://peerj.com/articles/cs-341/), PeerJ Computer Science 7:e341, *Mona Alshahrani, Maha A. Thafar, Magbubah Essack*
+1. [**SSFG：随机缩放特征与梯度以正则化图卷积网络**](https://arxiv.org/abs/2102.10338), *Haimin Zhang, Min Xu*
-1. [**MoTSE: an interpretable task similarity estimator for small molecular property prediction tasks**](https://www.biorxiv.org/content/10.1101/2021.01.13.426608v2), bioRxiv 2021.01.13.426608, *Han Li, Xinyi Zhao, Shuya Li, Fangping Wan, Dan Zhao, Jianyang Zeng*
+1. [**知识图谱嵌入在生物医学数据中的应用与评估**](https://peerj.com/articles/cs-341/), PeerJ Computer Science 7:e341, *Mona Alshahrani, Maha A. Thafar, Magbubah Essack*
-1. [**Reinforcement Learning For Data Poisoning on Graph Neural Networks**](https://arxiv.org/abs/2102.06800), *Jacob Dineen, A S M Ahsan-Ul Haque, Matthew Bielskas*
+1. [**MoTSE：面向小分子性质预测任务的可解释任务相似度估计器**](https://www.biorxiv.org/content/10.1101/2021.01.13.426608v2), bioRxiv 2021.01.13.426608, *Han Li, Xinyi Zhao, Shuya Li, Fangping Wan, Dan Zhao, Jianyang Zeng*
-1. [**Generalising Recursive Neural Models by Tensor Decomposition**](https://github.com/danielecastellana22/tensor-tree-nn), IJCNN'20, *Daniele Castellana, Davide Bacciu*
+1. [**面向图神经网络数据投毒的强化学习**](https://arxiv.org/abs/2102.06800), *Jacob Dineen, A S M Ahsan-Ul Haque, Matthew Bielskas*
-1. [**Tensor Decompositions in Recursive Neural Networks for Tree-Structured Data**](https://github.com/danielecastellana22/tensor-tree-nn), ESANN'20, *Daniele Castellana, Davide Bacciu*
+1. [**通过张量分解推广递归神经模型**](https://github.com/danielecastellana22/tensor-tree-nn), IJCNN'20, *Daniele Castellana, Davide Bacciu*
-1. [**Combining Self-Organizing and Graph Neural Networks for Modeling Deformable Objects in Robotic Manipulation**](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7806087/), Frotiers in Robotics and AI, *Valencia, Angel J., and Pierre Payeur*
+1. [**树结构数据递归神经网络中的张量分解**](https://github.com/danielecastellana22/tensor-tree-nn), ESANN'20, *Daniele Castellana, Davide Bacciu*
-1. [**Joint stroke classification and text line grouping in online handwritten documents with edge pooling attention networks**](https://www.sciencedirect.com/science/article/abs/pii/S0031320321000467), Pattern Recognition, *Jun-Yu Ye, Yan-Ming Zhang, Qing Yang, Cheng-Lin Liu*
+1. [**结合自组织与图神经网络建模机器人操作中的可变形物体**](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7806087/), Frotiers in Robotics and AI, *Valencia, Angel J., and Pierre Payeur*
-1. [**Toward Accurate Predictions of Atomic Properties via Quantum Mechanics Descriptors Augmented Graph Convolutional Neural Network: Application of This Novel Approach in NMR Chemical Shifts Predictions**](https://pubs.acs.org/doi/full/10.1021/acs.jpclett.0c02654), The Journal of Physical Chemistry Letters, *Peng Gao, Jie Zhang, Yuzhu Sun, and Jianguo Yu*
+1. [**基于边池化注意力网络的在线手写文档笔画分类与文本行分组**](https://www.sciencedirect.com/science/article/abs/pii/S0031320321000467), Pattern Recognition, *Jun-Yu Ye, Yan-Ming Zhang, Qing Yang, Cheng-Lin Liu*
-1. [**A Graph Neural Network to Model User Comfort in Robot Navigation**](https://arxiv.org/abs/2102.08863), *Pilar Bachiller, Daniel Rodriguez-Criado, Ronit R. Jorvekar, Pablo Bustos, Diego R. Faria, Luis J. Manso*
+1. [**借助量子力学描述符增强图卷积神经网络准确预测原子性质：该新方法在 NMR 化学位移预测中的应用**](https://pubs.acs.org/doi/full/10.1021/acs.jpclett.0c02654), The Journal of Physical Chemistry Letters, *Peng Gao, Jie Zhang, Yuzhu Sun, and Jianguo Yu*
-1. [**Medical Entity Disambiguation Using Graph Neural Networks**](https://arxiv.org/abs/2104.01488), *Alina Vretinaris, Chuan Lei, Vasilis Efthymiou, Xiao Qin, Fatma Özcan*
+1. [**建模机器人导航中用户舒适度的图神经网络**](https://arxiv.org/abs/2102.08863), *Pilar Bachiller, Daniel Rodriguez-Criado, Ronit R. Jorvekar, Pablo Bustos, Diego R. Faria, Luis J. Manso*
-1. [**Chemistry-informed Macromolecule Graph Representation for Similarity Computation and Supervised Learning**](https://arxiv.org/abs/2103.02565), *Somesh Mohapatra, Joyce An, Rafael Gómez-Bombarelli*
+1. [**利用图神经网络进行医学实体消歧**](https://arxiv.org/abs/2104.01488), *Alina Vretinaris, Chuan Lei, Vasilis Efthymiou, Xiao Qin, Fatma Özcan*
-1. [**Characterizing and Forecasting User Engagement with In-app Action Graph: A Case Study of Snapchat**](https://arxiv.org/pdf/1906.00355.pdf), *Yozen Liu, Xiaolin Shi, Lucas Pierce, Xiang Ren*
+1. [**化学信息引导的大分子图表示用于相似度计算与监督学习**](https://arxiv.org/abs/2103.02565), *Somesh Mohapatra, Joyce An, Rafael Gómez-Bombarelli*
-1. [**GIPA: General Information Propagation Algorithm for Graph Learning**](https://arxiv.org/abs/2105.06035), *Qinkai Zheng, Houyi Li, Peng Zhang, Zhixiong Yang, Guowei Zhang, Xintan Zeng, Yongchao Liu*
+1. [**基于应用内动作图刻画与预测用户参与度：以 Snapchat 为例**](https://arxiv.org/pdf/1906.00355.pdf), *Yozen Liu, Xiaolin Shi, Lucas Pierce, Xiang Ren*
-1. [**Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification**](https://arxiv.org/abs/2103.11794), NAACL'21, *Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He, Bowen Zhou*
+1. [**GIPA：面向图学习的通用信息传播算法**](https://arxiv.org/abs/2105.06035), *Qinkai Zheng, Houyi Li, Peng Zhang, Zhixiong Yang, Guowei Zhang, Xintan Zeng, Yongchao Liu*
-1. [**Enhancing Scientific Papers Summarization with Citation Graph**](https://arxiv.org/abs/2104.03057), AAAI'21, *Chenxin An, Ming Zhong, Yiran Chen, Danqing Wang, Xipeng Qiu, Xuanjing Huang*
+1. [**基于多棵依赖树的图集成学习用于方面级情感分类**](https://arxiv.org/abs/2103.11794), NAACL'21, *Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He, Bowen Zhou*
-1. [**Improving Graph Representation Learning by Contrastive Regularization**](https://arxiv.org/pdf/2101.11525.pdf), *Kaili Ma, Haochen Yang, Han Yang, Tatiana Jin, Pengfei Chen, Yongqiang Chen, Barakeel Fanseu Kamhoua, James Cheng*
+1. [**利用引用图增强科学论文摘要**](https://arxiv.org/abs/2104.03057), AAAI'21, *Chenxin An, Ming Zhong, Yiran Chen, Danqing Wang, Xipeng Qiu, Xuanjing Huang*
-1. [**Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework**](https://arxiv.org/pdf/2103.02885.pdf), WWW'21, *Cheng Yang, Jiawei Liu, Chuan Shi*
+1. [**通过对比正则化改进图表示学习**](https://arxiv.org/pdf/2101.11525.pdf), *Kaili Ma, Haochen Yang, Han Yang, Tatiana Jin, Pengfei Chen, Yongqiang Chen, Barakeel Fanseu Kamhoua, James Cheng*
-1. [**VIKING: Adversarial Attack on Network Embeddings via Supervised Network Poisoning**](https://arxiv.org/pdf/2102.07164.pdf), PAKDD'21, *Viresh Gupta, Tanmoy Chakraborty*
+1. [**提取图神经网络的知识并超越它：一种有效的知识蒸馏框架**](https://arxiv.org/pdf/2103.02885.pdf), WWW'21, *Cheng Yang, Jiawei Liu, Chuan Shi*
-1. [**Knowledge Graph Embedding using Graph Convolutional Networks with Relation-Aware Attention**](https://arxiv.org/pdf/2102.07200.pdf), *Nasrullah Sheikh, Xiao Qin, Berthold Reinwald, Christoph Miksovic, Thomas Gschwind, Paolo Scotton*
+1. [**VIKING：通过监督式网络投毒对网络嵌入进行对抗攻击**](https://arxiv.org/pdf/2102.07164.pdf), PAKDD'21, *Viresh Gupta, Tanmoy Chakraborty*
-1. [**SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks**](https://arxiv.org/pdf/2102.05034.pdf), *Bahare Fatemi, Layla El Asri, Seyed Mehran Kazemi*
+1. [**基于关系感知注意力的图卷积网络知识图谱嵌入**](https://arxiv.org/pdf/2102.07200.pdf), *Nasrullah Sheikh, Xiao Qin, Berthold Reinwald, Christoph Miksovic, Thomas Gschwind, Paolo Scotton*
-1. [**Finding Needles in Heterogeneous Haystacks**](https://homepage.divms.uiowa.edu/~badhikari/assets/doc/papers/CONGCNIAAI2021.pdf), AAAI'21, *Bijaya Adhikari, Liangyue Li, Nikhil Rao, Karthik Subbian*
+1. [**SLAPS：自监督改进图神经网络的结构学习**](https://arxiv.org/pdf/2102.05034.pdf), *Bahare Fatemi, Layla El Asri, Seyed Mehran Kazemi*
-1. [**RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning**](https://arxiv.org/abs/2105.00795), IJCAI 2021, *Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Eunho Yang, Sung-Ju Hwang, Jinwoo Shin*
+1. [**在异构草堆中寻找针**](https://homepage.divms.uiowa.edu/~badhikari/assets/doc/papers/CONGCNIAAI2021.pdf), AAAI'21, *Bijaya Adhikari, Liangyue Li, Nikhil Rao, Karthik Subbian*
-1. [**Accurate Prediction of Free Solvation Energy of Organic Molecules via Graph Attention Network and Message Passing Neural Network from Pairwise Atomistic Interactions**](https://arxiv.org/abs/2105.02048), *Ramin Ansari, Amirata Ghorbani*
+1. [**RetCL：基于对比学习的逆合成选择方法**](https://arxiv.org/abs/2105.00795), IJCAI 2021, *Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Eunho Yang, Sung-Ju Hwang, Jinwoo Shin*
-1. [**DIPS-Plus: The Enhanced Database of Interacting Protein Structures for Interface Prediction**](https://arxiv.org/abs/2106.04362), *Alex Morehead, Chen Chen, Ada Sedova, Jianlin Cheng*
+1. [**基于原子对相互作用通过图注意力网络与消息传递神经网络精确预测有机分子自由溶剂化能**](https://arxiv.org/abs/2105.02048), *Ramin Ansari, Amirata Ghorbani*
-1. [**Coreference-Aware Dialogue Summarization**](https://arxiv.org/abs/2106.08556), SIGDIAL'21, *Zhengyuan Liu, Ke Shi, Nancy F. Chen*
+1. [**DIPS-Plus：用于界面预测的增强型相互作用蛋白质结构数据库**](https://arxiv.org/abs/2106.04362), *Alex Morehead, Chen Chen, Ada Sedova, Jianlin Cheng*
-1. [**Document Structure aware Relational Graph Convolutional Networks for Ontology Population**](https://arxiv.org/abs/2104.12950), arXiv, *Abhay M Shalghar, Ayush Kumar, Balaji Ganesan, Aswin Kannan, Shobha G*
+1. [**共指感知的对话摘要**](https://arxiv.org/abs/2106.08556), SIGDIAL'21, *Zhengyuan Liu, Ke Shi, Nancy F. Chen*
-1. [**Covid-19 Detection from Chest X-ray and Patient Metadata using Graph Convolutional Neural Networks**](https://arxiv.org/abs/2105.09720), *Thosini Bamunu Mudiyanselage, Nipuna Senanayake, Chunyan Ji, Yi Pan, Yanqing Zhang*
+1. [**面向本体填充的文档结构感知关系图卷积网络**](https://arxiv.org/abs/2104.12950), arXiv, *Abhay M Shalghar, Ayush Kumar, Balaji Ganesan, Aswin Kannan, Shobha G*
-1. [**Rossmann-toolbox: a deep learning-based protocol for the prediction and design of cofactor specificity in Rossmann fold proteins**](https://academic.oup.com/bib/advance-article/doi/10.1093/bib/bbab371/6375059), Briefings in Bioinformatics, *Kamil Kaminski, Jan Ludwiczak, Maciej Jasinski, Adriana Bukala, Rafal Madaj, Krzysztof Szczepaniak, Stanislaw Dunin-Horkawicz*
+1. [**利用图卷积神经网络从胸部 X 光与患者元数据检测 Covid-19**](https://arxiv.org/abs/2105.09720), *Thosini Bamunu Mudiyanselage, Nipuna Senanayake, Chunyan Ji, Yi Pan, Yanqing Zhang*
-1. [**LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations**](https://arxiv.org/pdf/2106.01093.pdf), ACL'21, *Ruisheng Cao, Lu Chen, Zhi Chen, Yanbin Zhao, Su Zhu, Kai Yu*
+1. [**Rossmann-toolbox：基于深度学习的 Rossmann 折叠蛋白辅因子特异性预测与设计协议**](https://academic.oup.com/bib/advance-article/doi/10.1093/bib/bbab371/6375059), Briefings in Bioinformatics, *Kamil Kaminski, Jan Ludwiczak, Maciej Jasinski, Adriana Bukala, Rafal Madaj, Krzysztof Szczepaniak, Stanislaw Dunin-Horkawicz*
-1. [**Enhancing Graph Neural Networks via auxiliary training for semi-supervised node classification**](https://www.sciencedirect.com/science/article/pii/S0950705121001477), Knowledge-Based System'21, *Yao Wu, Yu Song, Hong Huang, Fanghua Ye, Xing Xie, Hai Jin*
+1. [**LGESQL：融合局部与非局部关系的线图增强 Text-to-SQL 模型**](https://arxiv.org/pdf/2106.01093.pdf), ACL'21, *Ruisheng Cao, Lu Chen, Zhi Chen, Yanbin Zhao, Su Zhu, Kai Yu*
-1. [**Modeling Graph Node Correlations with Neighbor Mixture Models**](https://arxiv.org/pdf/2103.15966.pdf), *Linfeng Liu, Michael C. Hughes, Li-Ping Liu*
+1. [**通过辅助训练增强图神经网络用于半监督节点分类**](https://www.sciencedirect.com/science/article/pii/S0950705121001477), Knowledge-Based System'21, *Yao Wu, Yu Song, Hong Huang, Fanghua Ye, Xing Xie, Hai Jin*
-1. [**COMBINING PHYSICS AND MACHINE LEARNING FOR NETWORK FLOW ESTIMATION**](https://openreview.net/pdf/9dc2744a465941220de07cf308acf822ec8aaa64.pdf), ICLR'21, *Arlei Silva, Furkan Kocayusufoglu, Saber Jafarpour, Francesco Bullo, Ananthram Swami, Ambuj Singh*
+1. [**使用邻居混合模型建模图节点相关性**](https://arxiv.org/pdf/2103.15966.pdf), *Linfeng Liu, Michael C. Hughes, Li-Ping Liu*
-1. [**A Classification Method for Academic Resources Based on a Graph Attention Network**](https://www.mdpi.com/1999-5903/13/3/64/htm), Future Internet'21, *Jie Yu, Yaliu Li, Chenle Pan and Junwei Wang*
+1. [**结合物理与机器学习进行网络流量估计**](https://openreview.net/pdf/9dc2744a465941220de07cf308acf822ec8aaa64.pdf), ICLR'21, *Arlei Silva, Furkan Kocayusufoglu, Saber Jafarpour, Francesco Bullo, Ananthram Swami, Ambuj Singh*
-1. [**Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture**](https://arxiv.org/abs/2103.03330), *Seung Won Min, Kun Wu, Sitao Huang, Mert Hidayetoğlu, Jinjun Xiong, Eiman Ebrahimi, Deming Chen, Wen-mei Hwu*
+1. [**基于图注意力网络的学术资源分类方法**](https://www.mdpi.com/1999-5903/13/3/64/htm), Future Internet'21, *Jie Yu, Yaliu Li, Chenle Pan and Junwei Wang*
-1. [**Graph Attention Multi-Layer Perception**](https://github.com/PKU-DAIR/GAMLP/blob/main/GAMLP.pdf), *Wentao Zhang, Ziqi Yin, Zeang Sheng, Wen Ouyang, Xiaosen Li, Yangyu Tao, Zhi Yang, Bin Cui*
+1. [**采用面向 GPU 的数据通信架构训练大规模图卷积网络**](https://arxiv.org/abs/2103.03330), *Seung Won Min, Kun Wu, Sitao Huang, Mert Hidayetoğlu, Jinjun Xiong, Eiman Ebrahimi, Deming Chen, Wen-mei Hwu*
-1. [**GNNLens: A Visual Analytics Approach for Prediction Error Diagnosis of Graph Neural Networks**](https://arxiv.org/abs/2011.11048v5), *Zhihua Jin, Yong Wang, Qianwen Wang, Yao Ming, Tengfei Ma, Huamin Qu*
+1. [**图注意力多层感知**](https://github.com/PKU-DAIR/GAMLP/blob/main/GAMLP.pdf), *Wentao Zhang, Ziqi Yin, Zeang Sheng, Wen Ouyang, Xiaosen Li, Yangyu Tao, Zhi Yang, Bin Cui*
-1. [**How Attentive are Graph Attention Networks?**](https://arxiv.org/pdf/2105.14491.pdf), *Shaked Brody, Uri Alon, Eran Yahav*, [code](https://github.com/tech-srl/how_attentive_are_gats)
+1. [**GNNLens：用于图神经网络预测误差诊断的可视分析方法**](https://arxiv.org/abs/2011.11048v5), *Zhihua Jin, Yong Wang, Qianwen Wang, Yao Ming, Tengfei Ma, Huamin Qu*
-1. [**SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks**](https://arxiv.org/pdf/2301.03512.pdf), *Thomas Monninger\*, Julian Schmidt\*, Jan Rupprecht, David Raba, Julian Jordan, Daniel Frank, Steffen Staab, Klaus Dietmayer*, [code](https://github.com/schmidt-ju/scene), \*co-first authors
+1. [**图注意力网络有多「注意力」？**](https://arxiv.org/pdf/2105.14491.pdf), *Shaked Brody, Uri Alon, Eran Yahav*, [代码](https://github.com/tech-srl/how_attentive_are_gats)
+
+1. [**SCENE：使用异构图神经网络推理交通场景**](https://arxiv.org/pdf/2301.03512.pdf), *Thomas Monninger\*, Julian Schmidt\*, Jan Rupprecht, David Raba, Julian Jordan, Daniel Frank, Steffen Staab, Klaus Dietmayer*, [代码](https://github.com/schmidt-ju/scene), \*共同第一作者