Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions
This addresses the challenge of handling evolving graphs in domains like bioinformatics and social networks by automating edge specification, though it is incremental as it builds on existing methods like temporal point processes and variational autoencoders.
The paper tackles the problem of inferring temporal attention in dynamic graphs without relying on expensive and suboptimal human-specified edges, using a model based on temporal point processes and variational autoencoders that learns from node interactions, and it outperforms baselines in dynamic link prediction tasks on two datasets.
Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks. We consider a common case in which edges can be short term interactions (e.g., messaging) or long term structural connections (e.g., friendship). In practice, long term edges are often specified by humans. Human-specified edges can be both expensive to produce and suboptimal for the downstream task. To alleviate these issues, we propose a model based on temporal point processes and variational autoencoders that learns to infer temporal attention between nodes by observing node communication. As temporal attention drives between-node feature propagation, using the dynamics of node interactions to learn this key component provides more flexibility while simultaneously avoiding issues associated with human-specified edges. We also propose a bilinear transformation layer for pairs of node features instead of concatenation, typically used in prior work, and demonstrate its superior performance in all cases. In experiments on two datasets in the dynamic link prediction task, our model often outperforms the baseline model that requires a human-specified graph. Moreover, our learned attention is semantically interpretable and infers connections similar to actual graphs.