A Topological Perspective on Demystifying GNN-Based Link Prediction Performance

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 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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
与落完成签到,获得积分10
1秒前
1秒前
Dora完成签到 ,获得积分10
1秒前
qmx发布了新的文献求助10
1秒前
科研通AI2S应助hhh采纳,获得10
2秒前
2秒前
王线性完成签到,获得积分10
5秒前
亦玉完成签到,获得积分10
7秒前
化学胖子完成签到,获得积分10
7秒前
等风的人发布了新的文献求助10
7秒前
忍冬完成签到,获得积分10
7秒前
目眩完成签到,获得积分10
8秒前
熊猫发布了新的文献求助10
8秒前
Dain完成签到,获得积分10
8秒前
wahaha完成签到 ,获得积分10
8秒前
万能图书馆应助guyanlong采纳,获得30
9秒前
吉祥应助忍冬采纳,获得10
11秒前
11秒前
你好完成签到 ,获得积分10
12秒前
zjq完成签到 ,获得积分10
14秒前
15秒前
华仔应助等风的人采纳,获得10
15秒前
Kawhichan完成签到,获得积分10
16秒前
sddq完成签到,获得积分10
17秒前
17秒前
hhh发布了新的文献求助10
18秒前
打打应助水博士采纳,获得10
21秒前
vivianzzz发布了新的文献求助20
22秒前
小潘发布了新的文献求助10
22秒前
深情安青应助qmx采纳,获得10
23秒前
26秒前
天天快乐应助科研通管家采纳,获得10
26秒前
英俊的铭应助科研通管家采纳,获得10
27秒前
wanci应助科研通管家采纳,获得10
27秒前
顾矜应助科研通管家采纳,获得10
27秒前
YUYUYU应助科研通管家采纳,获得30
27秒前
汉堡包应助科研通管家采纳,获得10
27秒前
梓泽丘墟应助科研通管家采纳,获得10
27秒前
27秒前
思源应助科研通管家采纳,获得10
27秒前
高分求助中
The ACS Guide to Scholarly Communication 2500
Sustainability in Tides Chemistry 2000
Pharmacogenomics: Applications to Patient Care, Third Edition 1000
Studien zur Ideengeschichte der Gesetzgebung 1000
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Threaded Harmony: A Sustainable Approach to Fashion 810
Genera Insectorum: Mantodea, Fam. Mantidæ, Subfam. Hymenopodinæ (Classic Reprint) 800
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3085517
求助须知:如何正确求助?哪些是违规求助? 2738369
关于积分的说明 7549389
捐赠科研通 2388127
什么是DOI,文献DOI怎么找? 1266316
科研通“疑难数据库(出版商)”最低求助积分说明 613412
版权声明 598591