Representation learning in dynamic graphs is a challenging problem because the topology of graph and node features vary at different time. This requires the model to be able to effectively capture both graph topology information and temporal information. Most existing works are built on recurrent neural networks (RNNs), which are used to exact temporal information of dynamic graphs, and thus they inherit the same drawbacks of RNNs. In this paper, we propose Learning to Evolve on Dynamic Graphs (LEDG) - a novel algorithm that jointly learns graph information and time information. Specifically, our approach utilizes gradient-based meta-learning to learn updating strategies that have better generalization ability than RNN on snapshots. It is model-agnostic and thus can train any message passing based graph neural network (GNN) on dynamic graphs. To enhance the representation power, we disentangle the embeddings into time embeddings and graph intrinsic embeddings. We conduct experiments on various datasets and down-stream tasks, and the experimental results validate the effectiveness of our method.
A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning
North China Electric Power University(华北电力大学);Beijing University of Posts and Telecommunications(北京邮电大学);Beihang University(北京航空航天大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校)
Co-Evolution-Based Metal-Binding Residue Prediction with Graph Neural Networks
Faculty of Computer Engineering, University of Isfahan(伊斯法罕大学计算机工程学院);School of Computer Science and Centre for Machine Intelligence, University of Sheffield(谢菲尔德大学计算机科学学院和智能中心);Institute of Cyberspace Security, College of Information Engineering, Zhejiang University of Technology(浙江工业大学信息工程学院网络空间安全研究所);School of Basic Medical Sciences and Institute of Medical Technology, Shanxi Medical University(山西医科大学基础医学学院和医学技术研究所);Institute of Big Data Science and Industry, Shanxi University(山西大学大数据科学与产业研究所)
M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification
Institute of Cyberspace Security, College of Information Engineering, Zhejiang University of Technology(浙江工业大学信息工程学院网络空间安全研究院);Department of Electrical Engineering, City University of Hong Kong(香港城市大学电子工程系)
Semantic Evolvement Enhanced Graph Autoencoder for Rumor Detection
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms
Tongji University(同济大学);Shanghai Research Institute for Intelligent Autonomous Systems(上海智能自主系统研究院);the Hong Kong University of Science and Technology(香港科技大学);SmartMore(思谋科技);University of Thessaloniki(塞萨洛尼基大学)