OOD-GNN: Out-of-Distribution Generalized Graph Neural Network

计算机科学 虚假关系 图形 判别式 人工智能 算法 理论计算机科学 模式识别(心理学) 机器学习
作者
Haoyang Li,Xin Wang,Ziwei Zhang,Wenwu Zhu
出处
期刊:IEEE Transactions on Knowledge and Data Engineering [IEEE Computer Society]
卷期号:35 (7): 7328-7340 被引量:93
标识
DOI:10.1109/tkde.2022.3193725
摘要

Graph neural networks (GNNs) have achieved impressive performance when testing and training graph data come from identical distribution. However, existing GNNs lack out-of-distribution generalization abilities so that their performance substantially degrades when there exist distribution shifts between testing and training graph data. To solve this problem, in this work, we propose an out-of-distribution generalized graph neural network (OOD-GNN) for achieving satisfactory performance on unseen testing graphs that have different distributions with training graphs. Our proposed OOD-GNN employs a novel nonlinear graph representation decorrelation method utilizing random Fourier features, which encourages the model to eliminate the statistical dependence between relevant and irrelevant graph representations through iteratively optimizing the sample graph weights and graph encoder. We further present a global weight estimator to learn weights for training graphs such that variables in graph representations are forced to be independent. The learned weights help the graph encoder to get rid of spurious correlations and, in turn, concentrate more on the true connection between learned discriminative graph representations and their ground-truth labels. We conduct extensive experiments to validate the out-of-distribution generalization abilities on two synthetic and 12 real-world datasets with distribution shifts. The results demonstrate that our proposed OOD-GNN significantly outperforms state-of-the-art baselines.
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
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
刚刚
刚刚
刚刚
共享精神的应助被Velunora采纳,获得200
刚刚
1秒前
故城发布了新的文献求助10
1秒前
Akim的应助被小天采纳,获得10
1秒前
Alice001完成签到 ,获得积分10
1秒前
1秒前
852的应助被温暖砖头采纳,获得10
1秒前
1秒前
研友_VZG7GZ的应助被szm采纳,获得10
2秒前
斯文败类的应助被szm采纳,获得10
2秒前
陈风完成签到,获得积分10
2秒前
天天快乐的应助被szm采纳,获得10
2秒前
科目三的应助被szm采纳,获得10
2秒前
Akim的应助被szm采纳,获得10
2秒前
DW的应助被szm采纳,获得10
2秒前
糖醋里脊的应助被szm采纳,获得10
2秒前
深情安青的应助被小友采纳,获得10
2秒前
3秒前
好柿花生完成签到 ,获得积分10
3秒前
yrx完成签到,获得积分10
3秒前
3秒前
玄都小法师完成签到,获得积分10
3秒前
风吹麦浪的应助被mht采纳,获得10
4秒前
4秒前
纵歌发布了新的文献求助10
4秒前
星辰坠于海的应助被李成昊采纳,获得10
5秒前
5秒前
途中完成签到,获得积分10
5秒前
在水一方的应助被jj采纳,获得10
5秒前
kin完成签到 ,获得积分10
5秒前
Lightblue3完成签到 ,获得积分10
5秒前
动听的小之完成签到 ,获得积分10
6秒前
现代的东蒽完成签到,获得积分10
6秒前
6秒前
6秒前
wuuv发布了新的文献求助10
7秒前
7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
John McDowells Bildungstheorie 800
Markov Decision Processes and Reinforcement Learning 700
八旗制度の研究 600
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 8170659
求助须知:如何正确求助?哪些是违规求助? 9563420
关于积分的说明 21770400
捐赠科研通 7762073
什么是DOI,文献DOI怎么找? 3430722
关于科研通互助平台的介绍 2554553
邀请新用户注册赠送积分活动 2475493