A curated list for awesome deep graph representation learning resources. Inspired by awesome-deep-learning-papers, awesome-deep-vision, awesome-architecture-search, awesome-self-supervised-learning-for-graphs, and awesome-deep-gnn.
The field of graph representation learning has grown at an incredible (and sometimes unwieldy) pace over the past seven years, transforming from a small subset of researchers working on a relatively niche topic to one of the fastest growing sub-areas of deep learning. - - William L. Hamilton
Graph representation learning (GRL) have recently become increasingly popular due to their ability to model relationships or interactions of complex systems. However GRL is still a nascent field in the Machine Learning community. Rather than providing overwhelming amount of papers, the goal of this repository is to provide a curated list of awesome GRL papers in recent top conference that we have read, as well as some intriguing blog posts and talks.
You are welcome to contribute this repo by contracting me or adding pull request.
Markdown formart:
Paper Name [[pdf]](link) [[code]](link)
Author 1, Author 2, Author 3.
Conference Year
*Taxonomy* (No more than 5 words)-
Graph Representation Learning [pdf]
William L. Hamilton
Book
Classical survey
-
Networks, Crowds, and Markets - Reasoning About a Highly Connected World [pdf]
D Easley, J Kleinberg
Book
Basic concepts on Networks
-
Network Science [pdf]
Albert-László Barabási
Book
Basic concepts on Networks
-
Relational inductive biases, deep learning, and graph networks [pdf]
Battaglia, Peter W and Hamrick, Jessica B, et al.
Arxiv 2018
Relational inductive biases on graphs
-
A comprehensive survey on graph neural networks [pdf]
Zonghan Wu, Shirui Pan, Chen, Guodong Long, Chengqi Zhang, Philip, S Yu
IEEE 2020
Survey
-
Self-Supervised Learning of Graph Neural Networks: A Unified Review [pdf]
Yaochen Xie, Zhao Xu, Jingtun Zhang, Zhengyang Wang, Shuiwang Ji
Arxiv 2021
Self-supervised learning
-
Combinatorial optimization and reasoning with graph neural networks [pdf]
Quentin Cappart, Didier Chételat, Elias Khalil, Andrea Lodi, Christopher Morris, Petar Veličković
IJCAI 2021
Survey on GNNs for combinatorial optimization and algorithmic reasoning
-
Adaptive Transfer Learning on Graph Neural Networks [pdf]
Xueting Han, Zhenhuan Huang, Bang An, Jing Bai
Transfer learning on GNNs
-
Tail-GNN: Tail-Node Graph Neural Networks [pdf]
Zemin Liu, Trung-Kien Nguyen, Yuan Fang
Long-tailed recognization on graph node degrees
-
Zero-shot Node Classification with Decomposed Graph Prototype Network [pdf]
Zheng Wang, Jialong Wang, Yuchen Guo, Zhiguo Gong
Zero-shot Node Classification
-
ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networks [pdf] [code]
Liang Qu, Huaisheng Zhu, Ruiqi Zheng, Yuhui Shi, Hongzhi Yin
Imbalanced Network Embedding
-
ROD: Reception-aware Online Distillation for Sparse Graphs [pdf]
Wentao Zhang, Yuezihan Jiang, Yang Li, et al.
New architecture of GNNs
-
Training Graph Neural Networks with 1000 Layers [pdf] [code]
Guohao Li, Matthias Müller, Bernard Ghanem, Vladlen Koltun
Deeper GNNs
-
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training [pdf]
Tianle Cai, Shengjie Luo, Keyulu Xu, Di He, Tie-Yan Liu, Liwei Wang
Training mechanism
-
Graph Contrastive Learning Automated [pdf] [code]
Yuning You, Tianlong Chen, Yang Shen, Zhangyang Wang
Graph contrastive learning
-
GNNAutoScale- Scalable and Expressive Graph Neural Networks via Historical Embeddings [pdf] [code]
Matthias Fey, Jan E. Lenssen, Frank Weichert, Jure Leskovec
Large scale GNNs
-
A Unified Lottery Ticket Hypothesis for Graph Neural Networks [pdf] [code]
Tianlong Chen, Yongduo Sui, Xuxi Chen, Aston Zhang, Zhangyang Wang
Sparse training on GNNs
-
On Explainability of Graph Neural Networks via Subgraph Explorations [pdf] [code]
Hao Yuan, Haiyang Yu, Jie Wang, Kang Li, Shuiwang Ji
Explanations of GNNs
-
Elastic Graph Neural Networks [pdf] [code]
Xiaorui Liu, Wei Jin, Yao Ma, Yaxin Li, Hua Liu, Yiqi Wang, Ming Yan, Jiliang Tang
New architecture of GNNs
-
Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework [pdf] [code]
Cheng Yang, Jiawei Liu, Chuan Shi
Graph + knowledge distillation
-
Graph Contrastive Learning with Adaptive Augmentation [pdf] [code]
Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, Liang Wang
Graph contrastive learning
-
HDMI: High-order Deep Multiplex Infomax [pdf]
Baoyu Jing, Chanyoung Park, Hanghang Tong
Multiplex graph representation learning
-
HOW TO FIND YOUR FRIENDLY NEIGHBORHOOD: GRAPH ATTENTION DESIGN WITH SELF-SUPERVISION [pdf] [code]
Dongkwan Kim, Alice Oh
Graph attention mechanism
-
CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks [pdf] [code]
Jiaqi Ma, Bo Chang, Xuefei Zhang, Qiaozhu Mei
Representational and correlational roles of graphs
-
How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks [pdf]
Keyulu Xu, Mozhi Zhang, Jingling Li, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
Extrapolation
-
On the Bottleneck of Graph Neural Networks and its Practical Implications [pdf] [code]
Uri Alon, Eran Yahav
over-squashing on GNNs
-
Graph Random Neural Network for Semi-Supervised Learning on Graphs [pdf] [code]
Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie Tang
New architecture of GNNs
-
Graph Meta Learning via Local Subgraphs [pdf] [code]
Kexin Huang, Marinka Zitnik
Graph meta learning
-
Subgraph Neural Networks [pdf] [code]
Emily Alsentzer, Samuel G. Finlayson, Michelle M. Li, Marinka Zitnik
Subgraph GNNs
-
Rethinking pooling in graph neural networks [pdf] [code]
Diego Mesquita, Amauri H. Souza, Samuel Kaski
Rethingking pooloing in GNNs
-
Design Space for Graph Neural Networks [pdf] [code]
Jiaxuan You, Rex Ying, Jure Leskovec
Design space for GNNs
-
Handling Missing Data with Graph Representation Learning [pdf]
Jiaxuan You, Xiaobai Ma, Daisy Yi Ding, Mykel Kochenderfer, Jure Leskovec
Matrix completion using GNNs
-
Beyond Homophily in Graph Neural Networks- Current Limitations and Effective Designs [pdf] [code]
Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, Danai Koutra
Graph homophily
-
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks [pdf] [code]
Xiang Zhang, Marinka Zitnik
Graph robustness
-
Graph Contrastive Learning with Augmentations [pdf] [code]
Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang Shen
Graph contrastive learning
-
Self-Supervised Graph Transformer on Large-Scale Molecular Data [pdf]
Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbing Huang, Junzhou Huang
Graph transformer
-
Scalable Graph Neural Networks via Bidirectional Propagation [pdf] [code]
Ming Chen, Zhewei Wei, Bolin Ding, Yaliang Li, Ye Yuan, Xiaoyong Du, Ji-Rong Wen
Large scale GNNs
-
AM-GCN: Adaptive Multi-channel Graph Convolutional Networks [pdf] [code]
Xiao Wang, Meiqi Zhu, Deyu Bo, Peng Cui, Chuan Shi, Jian Pei
New architecture of GNNs
-
Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [pdf] [code]
Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Xiaojun Chang, Chengqi Zhang
Graph + time series
-
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training [pdf] [code]
Jiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang, Hongxia Yang, Ming Ding, Kuansan Wang, Jie Tang
Grapg contrastive learning
-
Towards Deeper Graph Neural Networks [pdf] [code]
Meng Liu, Hongyang Gao, Shuiwang Ji
Deeper GNNs
-
TinyGNN: Learning Efficient Graph Neural Networks [pdf]
Bencheng Yan, Chaokun Wang, Gaoyang Guo, Yunkai Lou
Large scale GNNs
-
XGNN: Towards Model-Level Explanations of Graph Neural Networks [pdf]
Hao Yuan, Jiliang Tang, Xia Hu, Shuiwang Ji
Explanations of GNNs
-
Beyond Low-frequency Information in Graph Convolutional Networks [pdf] [code]
Deyu Bo, Xiao Wang, Chuan Shi, Huawei Shen
New architecture of GNNs
-
Data Augmentation for Graph Neural Networks [pdf] [code]
Tong Zhao, Yozen Liu, Leonardo Neves, Oliver Woodford, Meng Jiang, Neil Shah
Graph data augmentation
-
GraphMix: Improved Training of GNNs for Semi-Supervised Learning [pdf] [code]
Vikas Verma, Meng Qu, Kenji Kawaguchi, Alex Lamb, Yoshua Bengio, Juho Kannala, Jian Tang
New architecture of GNNs
-
Identity-aware Graph Neural networks [pdf]
Jiaxuan You, Jonathan Gomes-Selman, Rex Ying, Jure Leskovec
New architecture of GNNs
-
Learning to Pre-train Graph Neural Networks [pdf] [code]
Yuanfu Lu, Xunqiang Jiang, Yuan Fang, Chuan Shi
Pre-training of GNNs
-
Contrastive Multi-View Representation Learning on Graphs [pdf]
Kaveh Hassani, Amir Hosein Khasahmadi
Graph contrastive learning
-
Graph Structure of Neural Networks [pdf] [code]
Jiaxuan You, Jure Leskovec, Kaiming He, Saining Xie
Graph structure
-
Robust Graph Representation Learning via Neural Sparsification [pdf]
Cheng Zheng, Bo Zong, Wei Cheng, et al.
Graph sparsification
-
Simple and Deep Graph Convolutional Networks [pdf] [code]
Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, Yaliang Li
New architecture of GNNs
-
When Does Self-Supervision Help Graph Convolutional Networks? [pdf] [code]
Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen
Graph self-supervision learning
-
DropEdge: Towards Deep Graph Convolutional Networks on Node Classification [pdf] [code]
Yu Rong, Wenbing Huang, Tingyang Xu, Junzhou Huang
New architecture of GNNs
-
Geom-GCN: Geometric Graph Convolutional Networks [pdf] [code]
Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang
New architecture of GNNs
-
GraphSAINT: Graph Sampling Based Inductive Learning Method [pdf] [code]
Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, Viktor Prasanna
Large scale GNNs
-
PairNorm: Tackling Oversmoothing in GNNs [pdf] [code]
Lingxiao Zhao, Leman Akoglu
Deeper GNNs
-
Strategies for Pre-training Graph Neural Networks [pdf] [code]
Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec
Graph pre-training
-
WHAT GRAPH NEURAL NETWORKS CANNOT LEARN: DEPTH VS WIDTH [pdf]
Andreas Loukas
Expressive power of GNNs
-
Neural Execution of Graph Algorithms [pdf]
Petar Veličković, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell
Algorithmic reasoning
-
What Can Neural Networks Reason About?[pdf]
Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
Algorithmic reasoning
-
GNNExplainer: Generating Explanations for Graph Neural Networks [pdf] [code]
Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec
Explanations of GNNs
-
Understanding Attention and Generalization in Graph Neural Networks [pdf] [code]
Boris Knyazev, Graham W. Taylor, Mohamed R. Amer
Understanding attention in GNNs
-
Collective dynamics of 'small-world' networks [pdf]
Watts, Duncan J and Strogatz, Steven H
Nature 1998
'Small-world phenomena'
-
Network motifs: simple building blocks of complex networks [pdf]
R. Milo, S. Shen-Orr, S. Itzkovitz, N. Kashtan, D. Chklovskii, U. Alon
Science 2002
Network motifs
-
Rolx: structural role extraction & mining in large graphs [pdf]
Keith Henderson, Brian Gallagher, Tina Eliassi-Rad, et al.
KDD 2012
Structural rele
-
Birds of a feather: Homophily in social networks [pdf]
McPherson, Miller and Smith-Lovin, Lynn and Cook, James M
Annual review of sociology 2001
Homophily phenomena
-
Network embedding as matrix factorization: Unifying deepwalk, line, pte, and node2vec [pdf] [code]
Qiu, Jiezhong and Dong, Yuxiao and Ma, Hao and Li, Jian and Wang, Kuansan and Tang, Jie
WSDM 2018
Unified framework for network embedding
-
Graph Neural Networks with Learnable Structural and Positional Representation [video]
Xavier Bresson 2021
-
Graph Representation Learning:Foundations, Methods, Applications and Systems [pdf]
KDD 2021 Graph tutorial
-
Graph Neural Networks: Algorithms and Applications [pdf]
Jian Tang 2021
-
Graph Representation Learning for Drug Discovery [pdf]
Jian Tang 2021
-
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs [pdf]
Jiong Zhu 2021
-
Theoretical Foundations of Graph Neural Networks [pdf] [video]
Petar Veličković 2021
-
Expressive Power of Graph Neural Networks [video]
Huawei Shen 2020
-
Graph Representation Learning for Algorithmic Reasoning [pdf] [video]
Petar Veličković 2020
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent