可扩展性
计算机科学
加权
节点(物理)
概化理论
计算
拓扑(电路)
公制(单位)
图形
透视图(图形)
相关性
理论计算机科学
算法
数学
人工智能
组合数学
数据库
统计
医学
放射科
工程类
结构工程
经济
运营管理
几何学
作者
Wang Yu,Tong Zhao,Yuying Zhao,Yunchao Liu,Xueqi Cheng,Neil Shah,Tyler Derr
出处
期刊:Cornell University - arXiv
日期:2023-01-01
被引量:1
标识
DOI:10.48550/arxiv.2310.04612
摘要
Graph Neural Networks (GNNs) have shown great promise in learning node embeddings for link prediction (LP). While numerous studies aim to improve the overall LP performance of GNNs, none have explored its varying performance across different nodes and its underlying reasons. To this end, we aim to demystify which nodes will perform better from the perspective of their local topology. Despite the widespread belief that low-degree nodes exhibit poorer LP performance, our empirical findings provide nuances to this viewpoint and prompt us to propose a better metric, Topological Concentration (TC), based on the intersection of the local subgraph of each node with the ones of its neighbors. We empirically demonstrate that TC has a higher correlation with LP performance than other node-level topological metrics like degree and subgraph density, offering a better way to identify low-performing nodes than using cold-start. With TC, we discover a novel topological distribution shift issue in which newly joined neighbors of a node tend to become less interactive with that node's existing neighbors, compromising the generalizability of node embeddings for LP at testing time. To make the computation of TC scalable, We further propose Approximated Topological Concentration (ATC) and theoretically/empirically justify its efficacy in approximating TC and reducing the computation complexity. Given the positive correlation between node TC and its LP performance, we explore the potential of boosting LP performance via enhancing TC by re-weighting edges in the message-passing and discuss its effectiveness with limitations. Our code is publicly available at https://github.com/YuWVandy/Topo_LP_GNN.
科研通智能强力驱动
Strongly Powered by AbleSci AI