核化边注意力：解决时间图神经网络中语义注意力模糊问题
Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks
AI总结：
KEAT通过核化边注意力机制提升时间图神经网络对时间依赖性的捕捉能力，实现更准确和可解释的信息传递。
摘要：
时间图神经网络（TGNNs）旨在捕捉动态图中结构和交互的演变以及时间。尽管许多模型通过编码或架构设计引入时间，但它们通常在纠缠的节点和边表示上计算注意力，未能反映它们各自的时间行为。节点嵌入缓慢演变，因为它们聚合长期的结构上下文，而边特征反映短暂的时间戳交互（例如消息、交易或交易）。这种不匹配导致语义注意力模糊，其中注意力权重无法区分缓慢漂移的节点状态和快速变化、信息丰富的边交互。因此，模型难以捕捉细粒度的时间依赖性，并且在时间相关性计算方面缺乏透明性。本文介绍了KEAT（用于时间图的核化边注意力），一种新的注意力公式，通过一系列连续时间核（包括拉普拉斯核、RBF核和可学习的MLP变体）调节边特征。KEAT保持了节点和边的各自角色，并无缝集成到Transformer式（例如DyGFormer）和消息传递（例如TGN）架构中。它在链接预测任务中比最近的DyGFormer提高18%，比TGN提高7%，使TGNNs中的信息传递更准确、可解释且时间敏感。
英文摘要：
Temporal Graph Neural Networks (TGNNs) aim to capture the evolving structure and timing of interactions in dynamic graphs. Although many models incorporate time through encodings or architectural design, they often compute attention over entangled node and edge representations, failing to reflect their distinct temporal behaviors. Node embeddings evolve slowly as they aggregate long-term structural context, while edge features reflect transient, timestamped interactions (e.g. messages, trades, or transactions). This mismatch results in semantic attention blurring, where attention weights cannot distinguish between slowly drifting node states and rapidly changing, information-rich edge interactions. As a result, models struggle to capture fine-grained temporal dependencies and provide limited transparency into how temporal relevance is computed. This paper introduces KEAT (Kernelized Edge Attention for Temporal Graphs), a novel attention formulation that modulates edge features using a family of continuous-time kernels, including Laplacian, RBF, and learnable MLP variant. KEAT preserves the distinct roles of nodes and edges, and integrates seamlessly with both Transformer-style (e.g., DyGFormer) and message-passing (e.g., TGN) architectures. It achieves up to 18% MRR improvement over the recent DyGFormer and 7% over TGN on link prediction tasks, enabling more accurate, interpretable and temporally aware message passing in TGNNs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
