Link Prediction Based on Graph Neural Networks

计算机科学 人工神经网络 图形 链接(几何体) 人工智能 理论计算机科学 计算机网络
作者
Muhan Zhang,Yixin Chen
出处
期刊:Cornell University - arXiv 被引量:772
标识
DOI:10.48550/arxiv.1802.09691
摘要

Link prediction is a key problem for network-structured data. Link prediction heuristics use some score functions, such as common neighbors and Katz index, to measure the likelihood of links. They have obtained wide practical uses due to their simplicity, interpretability, and for some of them, scalability. However, every heuristic has a strong assumption on when two nodes are likely to link, which limits their effectiveness on networks where these assumptions fail. In this regard, a more reasonable way should be learning a suitable heuristic from a given network instead of using predefined ones. By extracting a local subgraph around each target link, we aim to learn a function mapping the subgraph patterns to link existence, thus automatically learning a `heuristic' that suits the current network. In this paper, we study this heuristic learning paradigm for link prediction. First, we develop a novel $γ$-decaying heuristic theory. The theory unifies a wide range of heuristics in a single framework, and proves that all these heuristics can be well approximated from local subgraphs. Our results show that local subgraphs reserve rich information related to link existence. Second, based on the $γ$-decaying theory, we propose a new algorithm to learn heuristics from local subgraphs using a graph neural network (GNN). Its experimental results show unprecedented performance, working consistently well on a wide range of problems.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
Alvess完成签到 ,获得积分10
1秒前
共享精神应助123采纳,获得10
2秒前
大象发布了新的文献求助10
3秒前
3秒前
4秒前
5秒前
5秒前
西红柿发布了新的文献求助10
7秒前
大象完成签到,获得积分10
8秒前
8秒前
开朗艳一发布了新的文献求助10
8秒前
赘婿应助彭彭采纳,获得10
9秒前
深情安青应助科研通管家采纳,获得10
9秒前
沐言发布了新的文献求助10
9秒前
FashionBoy应助科研通管家采纳,获得10
9秒前
ding应助科研通管家采纳,获得10
9秒前
SciGPT应助科研通管家采纳,获得10
9秒前
9秒前
9秒前
隐形曼青应助科研通管家采纳,获得10
9秒前
丘比特应助科研通管家采纳,获得10
9秒前
丘比特应助怪咖采纳,获得10
9秒前
10秒前
lzz完成签到,获得积分10
10秒前
py999发布了新的文献求助10
11秒前
张演基完成签到,获得积分10
11秒前
sgqt发布了新的文献求助20
12秒前
三里墩头应助Muhammad采纳,获得10
13秒前
三里墩头应助Muhammad采纳,获得10
13秒前
完美世界应助开朗艳一采纳,获得10
13秒前
醒醒发布了新的文献求助10
14秒前
李健应助摩天大楼采纳,获得10
15秒前
15秒前
luoyuanhaolzu发布了新的文献求助10
15秒前
一点点晚风完成签到,获得积分10
15秒前
闪闪寄凡发布了新的文献求助30
16秒前
17秒前
dhjic完成签到,获得积分10
17秒前
18秒前
19秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975658
求助须知:如何正确求助?哪些是违规求助? 3519986
关于积分的说明 11200481
捐赠科研通 3256410
什么是DOI,文献DOI怎么找? 1798247
邀请新用户注册赠送积分活动 877490
科研通“疑难数据库(出版商)”最低求助积分说明 806376