计算机科学
嵌入
节点(物理)
邻接表
推论
邻接矩阵
算法
理论计算机科学
人工智能
图形
数据挖掘
结构工程
工程类
作者
Meng Qin,Chaorui Zhang,Bo Bob Bai,Gong Zhang,Dit‐Yan Yeung
标识
DOI:10.1109/tkde.2023.3238360
摘要
Temporal link prediction (TLP) is an inference task on dynamic graphs that predicts future topology using historical graph snapshots. Existing TLP methods are usually designed for unweighted graphs with fixed node sets. Some of them cannot be generalized to the prediction of weighted graphs with non-fixed node sets. Although several methods can still be used to predict weighted graphs, they can only derivelow-qualityprediction snapshots sensitive to large edge weights but fail to distinguish small and zero weights in adjacency matrices. In this study, we consider the challenginghigh-qualityTLP on weighted dynamic graphs and propose a novel inductive dynamic embedding aggregation (IDEA) method, inspired by the high-resolution video prediction. IDEA combines conventional error minimization objectives with a scale difference minimization objective, which can generatehigh-qualityweighted prediction snapshots, distinguishing differences among large, small, and zero weights in adjacency matrices. Since IDEA adopts an inductive dynamic embedding scheme with an attentive node aligning unit and adaptive embedding aggregation module, it can also tackle the TLP on weighted graphs even with non-fixed node sets. Experiments on datasets of various scenarios validate that IDEA can derivehigh-qualityprediction results for weighted dynamic graphs and tackle the variation of node sets.
科研通智能强力驱动
Strongly Powered by AbleSci AI