Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning

计算机科学 人工智能 人工神经网络 机器学习 图形 理论计算机科学
作者
Xiao Wang,Nian Liu,Hui Han,Chuan Shi
出处
期刊: [Association for Computing Machinery]
卷期号:: 1726-1736 被引量:644
标识
DOI:10.1145/3447548.3467415
摘要

Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits their wide use in reality since labels are usually scarce in real applications. Recently, contrastive learning, a self-supervised method, becomes one of the most exciting learning paradigms and shows great potential when there are no labels. In this paper, we study the problem of self-supervised HGNNs and propose a novel co-contrastive learning mechanism for HGNNs, named HeCo. Different from traditional contrastive learning which only focuses on contrasting positive and negative samples, HeCo employs cross-view contrastive mechanism. Specifically, two views of a HIN (network schema and meta-path views) are proposed to learn node embeddings, so as to capture both of local and high-order structures simultaneously. Then the cross-view contrastive learning, as well as a view mask mechanism, is proposed, which is able to extract the positive and negative embeddings from two views. This enables the two views to collaboratively supervise each other and finally learn high-level node embeddings. Moreover, two extensions of HeCo are designed to generate harder negative samples with high quality, which further boosts the performance of HeCo. Extensive experiments conducted on a variety of real-world networks show the superior performance of the proposed methods over the state-of-the-arts.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
ding的应助被霁月采纳,获得10
刚刚
Akim的应助被zhangxu采纳,获得50
刚刚
传奇3的应助被开心德地采纳,获得10
1秒前
Yoona发布了新的文献求助10
1秒前
1秒前
烧烤店在逃花肉完成签到,获得积分10
2秒前
2秒前
科研通AI6.4的应助被第一作者采纳,获得10
2秒前
Lucas的应助被尹兴亮采纳,获得10
2秒前
2秒前
Jasper的应助被老实白筠采纳,获得10
2秒前
大胆听莲发布了新的文献求助10
3秒前
阔达傀斗发布了新的文献求助10
3秒前
GPTea的应助被dipa采纳,获得20
5秒前
5秒前
yx完成签到,获得积分10
5秒前
rose完成签到,获得积分10
5秒前
H呀呀呀发布了新的文献求助10
6秒前
00发布了新的文献求助10
7秒前
7秒前
7秒前
微血管发布了新的文献求助10
7秒前
7秒前
7秒前
ABB完成签到,获得积分10
8秒前
8秒前
8秒前
8秒前
Oliver完成签到,获得积分10
8秒前
dua完成签到,获得积分10
8秒前
深情安青的应助被开心德地采纳,获得10
8秒前
zdenglong完成签到,获得积分10
8秒前
wx发布了新的文献求助10
9秒前
9秒前
小硕土川完成签到,获得积分10
9秒前
Jml完成签到 ,获得积分10
9秒前
youyouG完成签到,获得积分10
10秒前
ding的应助被向晚采纳,获得10
10秒前
嘻嘻哈哈的应助被Chen采纳,获得10
11秒前
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8187748
求助须知:如何正确求助?哪些是违规求助? 9575825
关于积分的说明 21843288
捐赠科研通 7785628
什么是DOI,文献DOI怎么找? 3435097
关于科研通互助平台的介绍 2559495
邀请新用户注册赠送积分活动 2482000