让时间图链接预测模型能跨数据集迁移，解决新图部署难题。
Transfer Learning for Temporal Link Prediction
- 用结构映射模块将图拓扑特征转为记忆嵌入，提升模型迁移性
- 新方法使带记忆的模型可在未见图上直接使用，无需重新训练
- 适合需要快速部署到新场景的时序图预测任务
图上的链接预测在推荐系统到药物发现等场景中有广泛应用。时序链接预测（TLP）旨在预测动态演化图中的未来链接，其复杂性源于图结构的时变特性。当前最优的TLP模型结合记忆模块与图神经网络，以学习节点到来的时序模式和图结构的演化规律。然而，记忆模块仅存储训练时见过的节点信息，导致这些模型无法直接迁移到全新图上进行测试与部署。本文研究了一种新的TLP迁移学习任务，提出适用于带记忆模型的可迁移方法。受结构信号对TLP任务具有信息量的启发，我们在现有TLP模型架构中引入结构映射模块，学习从图结构（拓扑）特征到记忆嵌入的映射。本工作为构建无记忆的基础模型（foundation model）在TLP任务上铺平了道路。
原文摘要 · Abstract (English)
Link prediction on graphs has applications spanning from recommender systems to drug discovery. Temporal link prediction (TLP) refers to predicting future links in a temporally evolving graph and adds additional complexity related to the dynamic nature of graphs. State-of-the-art TLP models incorporate memory modules alongside graph neural networks to learn both the temporal mechanisms of incoming nodes and the evolving graph topology. However, memory modules only store information about nodes seen at train time, and hence such models cannot be directly transferred to entirely new graphs at test time and deployment. In this work, we study a new transfer learning task for temporal link prediction, and develop transfer-effective methods for memory-laden models. Specifically, motivated by work showing the informativeness of structural signals for the TLP task, we augment a structural mapping module to the existing TLP model architectures, which learns a mapping from graph structural (topological) features to memory embeddings. Our work paves the way for a memory-free foundation model for TLP.
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。