EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
Aldo Pareja, Giacomo Domeniconi, Jie Chen et al. · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · 2020
Graph representation learning resurges as a trending research subject owing to the widespread use of deep learning for Euclidean data, which inspire various creative designs of neural networks in the non-Euclidean domain, particularly graphs. With the success of these graph neural networks (GNN) in the static setting, we approach further practical scenarios where the graph dynamically evolves. Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics. These methods require the knowledge of a node in the full time span (including both training and testing) and are less applicable to the frequent change of the node set. In some extreme scenarios, the node sets at different time steps may completely differ. To resolve this challenge, we propose EvolveGCN, which adapts the graph convolutional network (GCN) model along the temporal dimension without resorting to node embeddings. The proposed approach captures the dynamism of the graph sequence through using an RNN to evolve the GCN parameters. Two architectures are considered for the parameter evolution. We evaluate the proposed approach on tasks including link prediction, edge classification, and node classification. The experimental results indicate a generally higher performance of EvolveGCN compared with related approaches. The code is available at https://github.com/IBM/EvolveGCN.
Cited by 1,221 works. doi:10.1609/aaai.v34i04.5984
Authors
- Aldo Pareja
- Giacomo Domeniconi
- Jie Chen
- Tengfei Ma
- Toyotaro Suzumura
- Hiroki Kanezashi
- Tim Kaler
- Tao B. Schardl
- Charles E. Leiserson
References
- Nonlinear Dimensionality Reduction by Locally Linear Embedding
- Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
- Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering
- DeepWalk
- Graph Attention Networks
- Advances In Deep Learning On Graphs (Gsp'18 Workshop)
- LINE
- Spectral Networks and Locally Connected Networks on Graphs
- Targeted Branching for the Maximum Independent Set Problem Using Graph Neural Networks
- Neural Message Passing for Quantum Chemistry