提升时序图网络表达能力，让其更好预测节点间未来互动强度。
Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification
- 为每条消息引入源-目标识别，增强时序图网络对动态交互的建模能力。
- 新方法TGNv2在所有TGB数据集上显著超越原有模型和启发式方法。
- 适用于需要精准预测节点互动频率的场景，如社交关系演化分析。
尽管时序图网络（TGN）在动态节点分类和链接预测任务中表现良好，但在动态节点亲和力预测任务中仍表现不佳——该任务旨在预测两个节点未来互动的强度。事实上，简单的启发式方法如持续预测和基于真实标签的移动平均，始终显著优于TGN。基于此观察，我们发现对消息进行启发式计算同样具有竞争力，且优于TGN及所有现有时序图模型。本文证明，任何TGN形式都无法表示对消息的持续预测或移动平均，并提出通过在每个交互事件消息中加入源-目标识别来增强TGN表达能力。我们证明该改进是表示持续预测、移动平均及更广泛的自回归消息模型所必需的。所提出的TGNv2在所有时序图基准（TGB）动态节点亲和力预测数据集上均显著优于TGN及所有现有时序图模型。
原文摘要 · Abstract (English)
Despite the successful application of Temporal Graph Networks (TGNs) for tasks such as dynamic node classification and link prediction, they still perform poorly on the task of dynamic node affinity prediction -- where the goal is to predict 'how much' two nodes will interact in the future. In fact, simple heuristic approaches such as persistent forecasts and moving averages over ground-truth labels significantly and consistently outperform TGNs. Building on this observation, we find that computing heuristics over messages is an equally competitive approach, outperforming TGN and all current temporal graph (TG) models on dynamic node affinity prediction. In this paper, we prove that no formulation of TGN can represent persistent forecasting or moving averages over messages, and propose to enhance the expressivity of TGNs by adding source-target identification to each interaction event message. We show that this modification is required to represent persistent forecasting, moving averages, and the broader class of autoregressive models over messages. Our proposed method, TGNv2, significantly outperforms TGN and all current TG models on all Temporal Graph Benchmark (TGB) dynamic node affinity prediction datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。