通过记忆回溯与拓扑归因，解释时序图网络的预测依据。
Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution
- 构建拓扑归因树与记忆回溯树，追踪历史事件影响
- 在9个数据集上验证，解释结果更忠实于模型输出
- 适合关注时序图模型可解释性的研究人员
时序图在现实应用中无处不在，时序图网络（TGN）已实现优异的预测性能。理解哪些历史事件驱动了模型预测，有助于提升TGN的可信度。现有解释方法忽视了记忆模块——这一记录和更新节点历史的核心组件，导致过去事件的影响未被充分探索。为此，本文通过拓扑归因树和记忆回溯树来解释TGN的预测：拓扑归因树捕捉邻居及其记忆向量的影响，记忆回溯树量化历史事件如何塑造节点记忆向量。引入LRP方法，确保事件总贡献等于模型输出的logits。由于top-k选择可能因非线性映射导致不忠实，我们设计优化目标以识别关键事件。在涵盖节点属性预测、链接预测和图分类任务的9个时序图数据集上，实验表明该方法能提供忠实解释，优于现有先进基线。代码已公开于https://github.com/yazhengliu/MemExplainer。
原文摘要 · Abstract (English)
Temporal graphs are ubiquitous in real-world applications and Temporal Graph Networks (TGNs) have achieved superior predictive accuracy. Understanding which historical events drive model predictions can enhance trustworthiness of TGNs. Existing explanation methods overlook the memory module, the core component that records and updates node histories, leaving the influence of past events unexplored. To address this, we attribute TGNs predictions through the topology attribution tree and memory backtracking tree. The topology attribution tree captures the influence of neighbors and their memory vectors, then the memory backtracking tree quantifies how historical events shape node memory vectors. We apply the LRP in TGNs, ensuring that the total contribution of events equals the logits of model. Finally, top-k selection may be unfaithful due to the nonlinear mapping from logits to probabilities, we design optimization objectives to identify the important events. Experiments on nine temporal graph datasets, spanning node property prediction, link prediction tasks and graph classification tasks, show that our method provides faithful explanations and outperforms state-of-the-art baselines. The code is available at https://github.com/yazhengliu/MemExplainer
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。