提出SIGHT模型，让图神经网络在分布外场景下更可靠、可解释。
Spiking Graph Predictive Coding for Reliable OOD Generalization
- 通过脉冲图状态迭代纠错，捕捉预测不可靠的内部信号。
- 在多个图基准上提升准确率与不确定性估计性能。
- 适合高风险场景，可解释不确定性的来源。
图结构为建模基于网络的关系数据提供了强大基础，表达性强的图神经网络（GNN）能有效支持动态网络环境中的学习。然而，现实部署常受分布外（OOD）变化的阻碍，用户行为演变与内容语义变化导致特征分布和标注标准改变，引发不稳定或过度自信的预测，损害了面向公益的Web4Good应用所需的可信度。实现可靠的OOD泛化需要有原则且可解释的不确定性估计，但现有方法多为事后处理，对分布偏移不敏感，难以解释不确定性来源，尤其在高风险场景下。为此，我们提出脉冲图预测编码（SIGHT），一种用于可靠OOD泛化的不确定性感知插件式图学习模块。SIGHT通过对脉冲图状态进行迭代、误差驱动的修正，使模型能够暴露内部不匹配信号，揭示预测不可靠的位置。在多个图基准和多样化的OOD场景中，将SIGHT集成到GNN后，其持续提升了预测准确性、不确定性估计能力与可解释性。
原文摘要 · Abstract (English)
Graphs provide a powerful basis for modeling Web-based relational data, with expressive GNNs to support the effective learning in dynamic web environments. However, real-world deployment is hindered by pervasive out-of-distribution (OOD) shifts, where evolving user activity and changing content semantics alter feature distributions and labeling criteria. These shifts often lead to unstable or overconfident predictions, undermining the trustworthiness required for Web4Good applications. Achieving reliable OOD generalization demands principled and interpretable uncertainty estimation; however, existing methods are largely post-hoc, insensitive to distribution shifts, and unable to explain where uncertainty arises especially in high-stakes settings. To address these limitations, we introduce SpIking GrapH predicTive coding (SIGHT), an uncertainty-aware plug-in graph learning module for reliable OOD Generalization. SIGHT performs iterative, error-driven correction over spiking graph states, enabling models to expose internal mismatch signals that reveal where predictions become unreliable. Across multiple graph benchmarks and diverse OOD scenarios, SIGHT consistently enhances predictive accuracy, uncertainty estimation, and interpretability when integrated with GNNs.
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。