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.

翻译：时序图学习旨在建模图随时间演化的特性，近年来受到广泛关注并取得了显著性能。然而，现实中的图结构往往存在不完整和噪声问题，这阻碍了时序图网络（TGNs）学习到信息丰富的表示。图对比学习通过数据增强技术生成现有数据的合理变体，从而学习鲁棒表示。但基于规则的增强方法可能并非最优，因其缺乏可学习性，且未能充分利用下游任务的丰富信息。为解决这些问题，本文提出一种基于时序图序列预测的时间感知图结构学习（TGSL）方法，通过添加潜在时序边来为下游任务学习更优的图结构。具体而言，该方法基于历史观测交互预测时间感知的上下文嵌入，并利用Gumble-Top-K选择与此上下文嵌入最接近的候选边。此外，我们提出了多种候选采样策略以兼顾效率与多样性。进一步地，我们以端到端方式联合学习图结构与TGNs，并在优化后的图上进行推理。在时序链接预测基准上的大量实验表明，TGSL为流行的TGNs（如TGAT和GraphMixer）带来了显著性能提升，且优于其他针对时序图的对比学习方法。相关代码将在未来开源。