Learning to Evolve on Dynamic Graphs (Student Abstract)
Keywords:Graph Neural Network, Dynamic Graph, Meta-learning, Feature Disentanglement
AbstractRepresentation 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.
How to Cite
Xiang, X., Huang, T., & Wang, D. (2022). Learning to Evolve on Dynamic Graphs (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 13091-13092. https://doi.org/10.1609/aaai.v36i11.21682
AAAI Student Abstract and Poster Program