点击上方，选择星标或置顶，每天给你送干货！

阅读大概需要16分钟

跟随小博主，每天进步一丢丢

整理：专知

KDD 2019

1、Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

作者：Wei-Lin Chiang; Xuanqing Liu; Si Si; Yang Li; Samy Bengio; Cho-Jui Hsieh;

地址：https://arxiv.org/pdf/1905.07953.pdf

2、Conditional Random Field Enhanced Graph Convolutional Neural Networks

作者：Hongchang Gao; Jian Pei; Heng Huang;

地址：

https://www.kdd.org/kdd2019/accepted-papers/view/conditional-random-field-enhanced-graph-convolutional-neural-networks

3、DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification

作者：Jun Wu; Jingrui He; Jiejun Xu;

地址：

https://arxiv.org/abs/1906.02319?context=cs

4、GCN-MF: Disease-Gene Association Identification By Graph Convolutional Networks and Matrix Factorization

作者：Peng Han; Peng Yang; Peilin Zhao; Shuo Shang; Yong Liu; Jiayu Zhou; Xin Gao; Panos Kalnis;

地址：

https://www.kdd.org/kdd2019/accepted-papers/view/cluster-gcn-an-efficient-algorithm-for-training-deep-and-large-graph-convol

5、Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks

作者：Namyong Park; Andrey Kan; Xin Luna Dong; Tong Zhao; Christos Faloutsos;

地址：https://arxiv.org/abs/1905.08865

6、Graph Recurrent Networks with Attributed Random Walks

作者：Xiao Huang; Qingquan Song; Yuening Li; Xia Hu;

地址：

https://www.kdd.org/kdd2019/accepted-papers/view/graph-recurrent-networks-with-attributed-random-walks

7、Representation Learning for Attributed Multiplex Heterogeneous Network

作者：Yukuo Cen, Xu Zou, Jianwei Zhang, Hongxia Yang, Jingren Zhou, Jie Tang

论文：http://t.cn/Ai9I8OPE；

代码：http://t.cn/Ai9I8OPn；

NeurIPS2019

1、GNN Explainer: Generating Explanations for Graph Neural Networks 

作者：Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec

地址：https://arxiv.org/abs/1903.03894

2、Graph Transformer Networks 

作者：Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, Hyunwoo Kim

地址：

http://data.holdenhu.site/papers/graph/graph-transformer-networks.pdf

3、Can Graph Neural Networks Help Logic Reasoning?

作者：Yuyu Zhang, Xinshi Chen, Yuan Yang, Arun Ramamurthy, Bo Li, Yuan Qi, Le Song

地址：

https://kr2ml.github.io/2019/papers/KR2ML_2019_paper_22.pdf

ICCV 2019

1、DeepGCNs: Can GCNs Go as Deep as CNNs?

作者：Guohao Li, Matthias Müller, Ali Thabet, Bernard Ghanem

地址：https://arxiv.org/abs/1904.03751

2. Exploiting Spatial-temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks

作者：Yujun Cai, Liuhao Ge, Jun Liu, Jianfei Cai, Tat-Jen Cham, Junsong Yuan, Nadia Magnenat Thalmann;

地址：

https://cse.buffalo.edu/~jsyuan/papers/2019/Exploiting_Spatial-temporal_Relationships_for_3D_Pose_Estimation_via_Graph_Convolutional_Networks.pdf

3、Graph Convolutional Networks for Temporal Action Localization

作者：Runhao Zeng, Wenbing Huang, Mingkui Tan, Yu Rong, Peilin Zhao, Junzhou Huang, Chuang Gan;

地址：https://arxiv.org/abs/1909.03252

代码：https://github.com/alvinzeng/pgcn

4、Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition

作者：Tianshui Chen, Muxin Xu, Xiaolu Hui, Hefeng Wu, Liang Lin;

地址：https://arxiv.org/abs/1908.07325

代码和模型：https://github. com/HCPLab-SYSU/SSGRL

WWW 2019

1、Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts 

作者：Alessandro Epasto, Bryan Perozzi

地址：http://t.cn/AiukgqNA；

2、NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization

作者：Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Chi Wang, Kuansan Wang, Jie Tang

地址：http://t.cn/AiuF7p97；

3、Graph Neural Networks for Social Recommendation

作者：Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, Dawei Yin

地址：http://t.cn/AiuFAzVr；

4、Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

作者：Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Peng He, Paul Weng, Han Gao, Guihai Chen

地址：http://t.cn/EiVtzOj；

ICML 2019

1、 Compositional Fairness Constraints for Graph Embeddings 

作者：Avishek Joey Bose, William L. Hamilton

地址：http://t.cn/AiukgnqL

2、Graph Matching Networks for Learning the Similarity of Graph Structured Objects 

作者：Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, Pushmeet Kohli

地址：http://t.cn/ES9dZYU

3、GMNN: Graph Markov Neural Networks  

作者：Meng Qu, Yoshua Bengio, Jian Tang

地址：http://t.cn/EKOJK3x；

4、MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

作者：Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan

地址：http://t.cn/AiuFAY4V；

ACL 2019

1、Cognitive Graph for Multi-Hop Reading Comprehension at Scale  

作者：Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, Jie Tang

地址：http://t.cn/EKSfKkr；

2、Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model 

作者：Wei Li, Jingjing Xu, Yancheng He, Shengli Yan, Yunfang Wu, Xu Sun

地址：http://t.cn/AiuF26Ve；

3、Dynamically Fused Graph Network for Multi-hop Reasoning

作者：Yunxuan Xiao, Yanru Qu, Lin Qiu, Hao Zhou, Lei Li, Weinan Zhang, Yong Yu

地址：http://t.cn/EKR7rcy；

4、Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks  

作者：Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya, Partha Talukdar

论文：http://t.cn/EKR7rcy；

代码：http://t.cn/AiuF2k4G

5、Attention Guided Graph Convolutional Networks for Relation Extraction 

作者：Zhijiang Guo，Yan Zhang and Wei Lu

地址：

http://www.statnlp.org/paper/2019/attention-guided-graph-convolutional-networks-relation-extraction.html

6、Encoding Social Information with Graph Convolutional Networks for Political Perspective Detection in News Media

作者：Chang Li, Dan Goldwasser

地址：

https://www.cs.purdue.edu/homes/dgoldwas//downloads/papers/LiG_acl_2019.pdf

ICLR 2020

1、GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding 

作者：Chenhui Deng, Zhiqiang Zhao, Yongyu Wang, Zhiru Zhang, Zhuo Feng

地址：

https://arxiv.org/abs/1910.02370?context=cs

2、Strategies for Pre-training Graph Neural Networks 

作者：Weihua Hu，Bowen Liu，Joseph Gomes， Marinka Zitnik，Percy Liang， Vijay Pande,，Jure Leskovec

地址：

https://arxiv.org/abs/1905.12265?context=cs.LG

3、Geom-GCN：Geometric Graph Convolutional Networks

作者：Hongbin-Pei，Bingzhe-Wei，Kevin Chen-chuan

地址：

https://openreview.net/forum?id=S1e2agrFvS

4、Contrastive Learning of Structured World Models 

作者：Thomas Kipf, Elise van der Pol, Max Welling

地址：https://arxiv.org/abs/1911.12247

5、The Logical Expressiveness of Graph Neural Networks 

作者：Pablo Barceló, Egor V. Kostylev, Mikael Monet, Jorge Pérez, Juan Reutter, Juan Pablo Silva

地址：

https://openreview.net/forum?id=r1lZ7AEKvB

参考链接：

来源：数据派THU

https://mp.weixin.qq.com/s/61aXpF-ayJseBUzWnc6TZA

---

方便交流学习，备注：昵称-学校（公司）-方向，进入DL&NLP交流群。

方向有很多：机器学习、深度学习，python，情感分析、意见挖掘、句法分析、机器翻译、人机对话、知识图谱、语音识别等。

记得备注呦

推荐阅读：

【ACL 2019】腾讯AI Lab解读三大前沿方向及20篇入选论文

【一分钟论文】IJCAI2019 | Self-attentive Biaffine Dependency  Parsing

【一分钟论文】 NAACL2019-使用感知句法词表示的句法增强神经机器翻译

【一分钟论文】Semi-supervised Sequence Learning半监督序列学习

【一分钟论文】Deep Biaffine Attention for Neural Dependency Parsing

详解Transition-based Dependency parser基于转移的依存句法解析器

经验 | 初入NLP领域的一些小建议

学术 | 如何写一篇合格的NLP论文

干货 | 那些高产的学者都是怎样工作的？

一个简单有效的联合模型

近年来NLP在法律领域的相关研究工作

---

让更多的人知道你“在看”