通过时间图信息瓶颈优化图结构，提升动态网络中节点表示的泛化能力。
Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning
- 分两步优化节点邻域结构，增强图表示的丰富性与效率。
- 在4个真实数据集上，诱导设置下性能全面超越现有方法。
- 适合研究动态图表示学习、需要处理新节点的场景。
时序图学习对动态网络至关重要，其中节点和边随时间演变，新节点持续加入系统。在该场景下的归纳式表示学习面临两大挑战：有效表示未见节点，以及缓解噪声或冗余的图信息。本文提出GTGIB框架，将图结构学习（GSL）与时序图信息瓶颈（TGIB）结合。设计了一种新型两阶段基于GSL的结构增强器，以丰富并优化节点邻域，并通过理论证明和实验验证其有效性与高效性。TGIB通过变分近似推导出可计算的时序图信息瓶颈目标函数，扩展信息瓶颈原理至时序图，基于边和特征进行正则化，实现稳定高效的优化。基于GTGIB的模型在四个真实世界数据集上进行链接预测评估，在所有数据集中，诱导设置下均优于现有方法，且在同构设置下表现显著且一致提升。
原文摘要 · Abstract (English)
Temporal graph learning is crucial for dynamic networks where nodes and edges evolve over time and new nodes continuously join the system. Inductive representation learning in such settings faces two major challenges: effectively representing unseen nodes and mitigating noisy or redundant graph information. We propose GTGIB, a versatile framework that integrates Graph Structure Learning (GSL) with Temporal Graph Information Bottleneck (TGIB). We design a novel two-step GSL-based structural enhancer to enrich and optimize node neighborhoods and demonstrate its effectiveness and efficiency through theoretical proofs and experiments. The TGIB refines the optimized graph by extending the information bottleneck principle to temporal graphs, regularizing both edges and features based on our derived tractable TGIB objective function via variational approximation, enabling stable and efficient optimization. GTGIB-based models are evaluated to predict links on four real-world datasets; they outperform existing methods in all datasets under the inductive setting, with significant and consistent improvement in the transductive setting.
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。