UTG: Towards a Unified View of Snapshot and Event Based Models for Temporal Graphs
This work addresses the lack of comparison and integration between snapshot and event-based temporal graph models for researchers and practitioners, though it is incremental in unifying existing approaches rather than introducing a fundamentally new method.
The paper tackles the problem of isolated development of machine learning methods for snapshot-based and event-based temporal graph representations by introducing UTG, a unified framework that enables cross-application of models between representations and improves snapshot-based model performance in streaming settings. The results show that with UTG training, snapshot-based models can compete with event-based models on event datasets while being 10x faster during inference, though event-based methods still outperform due to structural feature utilization.
Many real world graphs are inherently dynamic, constantly evolving with node and edge additions. These graphs can be represented by temporal graphs, either through a stream of edge events or a sequence of graph snapshots. Until now, the development of machine learning methods for both types has occurred largely in isolation, resulting in limited experimental comparison and theoretical crosspollination between the two. In this paper, we introduce Unified Temporal Graph (UTG), a framework that unifies snapshot-based and event-based machine learning models under a single umbrella, enabling models developed for one representation to be applied effectively to datasets of the other. We also propose a novel UTG training procedure to boost the performance of snapshot-based models in the streaming setting. We comprehensively evaluate both snapshot and event-based models across both types of temporal graphs on the temporal link prediction task. Our main findings are threefold: first, when combined with UTG training, snapshot-based models can perform competitively with event-based models such as TGN and GraphMixer even on event datasets. Second, snapshot-based models are at least an order of magnitude faster than most event-based models during inference. Third, while event-based methods such as NAT and DyGFormer outperforms snapshot-based methods on both types of temporal graphs, this is because they leverage joint neighborhood structural features thus emphasizing the potential to incorporate these features into snapshotbased models as well. These findings highlight the importance of comparing model architectures independent of the data format and suggest the potential of combining the efficiency of snapshot-based models with the performance of event-based models in the future.