Temporal Graph Learning, which aims to model the time-evolving nature of graphs, has gained increasing attention and achieved remarkable performance recently. However, in reality, graph structures are often incomplete and noisy, which hinders temporal graph networks (TGNs) from learning informative representations. Graph contrastive learning uses data augmentation to generate plausible variations of existing data and learn robust representations. However, rule-based augmentation approaches may be suboptimal as they lack learnability and fail to leverage rich information from downstream tasks. To address these issues, we propose a Time-aware Graph Structure Learning (TGSL) approach via sequence prediction on temporal graphs, which learns better graph structures for downstream tasks through adding potential temporal edges. In particular, it predicts time-aware context embedding based on previously observed interactions and uses the Gumble-Top-K to select the closest candidate edges to this context embedding. Additionally, several candidate sampling strategies are proposed to ensure both efficiency and diversity. Furthermore, we jointly learn the graph structure and TGNs in an end-to-end manner and perform inference on the refined graph. Extensive experiments on temporal link prediction benchmarks demonstrate that TGSL yields significant gains for the popular TGNs such as TGAT and GraphMixer, and it outperforms other contrastive learning methods on temporal graphs. We will release the code in the future.

本研究提出了一种基于序列预测的 TGSL 方法来更好地学习下游任务的图结构，通过添加潜在的时间边、使用 Gumble-Top-K 来选择最接近上下文嵌入的候选边，以及提出若干候选采样策略，同时端到端联合学习图结构和 TGNs，实验结果表明 TGSL 可以显著提高 TGAT、GraphMixer 等热门 TGNs 的性能，且在时间图上优于其他对比学习方法。

基于时间序列预测的时序图结构学习