.png){kind=icon}
返回
Fair Contrastive Learning on Graphs
.png){kind=icon}
PRE
AI
DOI：10.1109/TSIPN.2022.3174953.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Node representation learning plays a critical role in learning over graphs. Specifically, the success of contrastive learning methods in unsupervised node representation learning has been demonstrated for various tasks, which has led to increase in attention towards the field. Despite the increasing popularity, fairness is widely under-explored in the area. Motivated by this, this study proposes novel fairness-aware graph augmentations based on adaptive feature masking and edge deletion, in order to mitigate the bias in graph contrastive learning. Different fairness notions on graphs are introduced in the study to guide the designs of the proposed adaptive augmentation schemes. Moreover, it is quantitatively shown that the proposed feature masking scheme can reduce the intrinsic bias. Experimental results on four real-world networks are presented to show that the introduced augmentation frameworks can improve group fairness measures together with comparable classification accuracy to state-of-the-art graph contrastive learning studies for node classification.
Keyword:
Machine learning on graphs
fairness
graph contrastive learning
data augmentation
node representation learning
期刊
IF:
4.9
论文数:
728
被引数:
1.9K
机构
引用论文
Sources of Segregation in Social Networks: A Novel Approach Using Facebook社交网络中的隔离来源: 使用Facebook的一种新方法
OAAI
.png){kind=icon}
OAAI分享收藏Conjugated heat transfer and temperature distributions in a gas turbine combustion liner under base-load operation基本负荷运行下燃气轮机燃烧衬里中的共轭传热和温度分布
PREAI
分享收藏Insurance activity and economic performance: Fresh evidence from asymmetric panel causality testsOAAI
OAAI分享收藏Tachykinin and Calcitonin Gene-Related Peptide Immunoreactivities and Mrnas in the Mammalian Enteric Nervous System and Sensory Ganglia哺乳动物肠神经系统和感觉神经节中的速激肽和降钙素基因相关肽的免疫反应性和mrna
PREAI
分享收藏
查看更多内容