提出新模型NAVIS，显著提升时序图节点亲和力预测效果
Revisiting Node Affinity Prediction in Temporal Graphs
- 将启发式方法建模为状态空间，设计虚拟状态机制
- 在TGB数据集上超越现有最先进模型及传统启发式方法
- 适合时序图学习、社交网络分析等需要动态关系预测的研究者
节点亲和力预测是时序图学习中的常见任务，广泛应用于社交网络、金融网络和推荐系统。近期工作尝试将先进的动态链接属性预测模型迁移至该任务，但简单启发式方法（如持续预测或移动平均）仍表现更优。本文分析了当前时序图神经网络在节点亲和力预测中训练困难的原因，并提出解决方案。基于这些方案，我们构建了NAVIS——一种利用虚拟状态进行节点亲和力预测的模型，其核心思想是揭示启发式方法与状态空间模型之间的等价性。尽管性能优异，NAVIS的训练仍具挑战性，因此我们进一步设计了一种新型损失函数。在TGB数据集上的实验表明，NAVIS优于当前最先进的方法，包括各类启发式方法。源代码已开源。
原文摘要 · Abstract (English)
Node affinity prediction is a common task that is widely used in temporal graph learning with applications in social and financial networks, recommender systems, and more. Recent works have addressed this task by adapting state-of-the-art dynamic link property prediction models to node affinity prediction. However, simple heuristics, such as Persistent Forecast or Moving Average, outperform these models. In this work, we analyze the challenges in training current Temporal Graph Neural Networks for node affinity prediction and suggest appropriate solutions. Combining the solutions, we develop NAViS - Node Affinity prediction model using Virtual State, by exploiting the equivalence between heuristics and state space models. While promising, training NAViS is non-trivial. Therefore, we further introduce a novel loss function for node affinity prediction. We evaluate NAViS on TGB and show that it outperforms the state-of-the-art, including heuristics. Our source code is available at https://github.com/orfeld415/NAVIS
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。