对抗制
计算机科学
图形
人工智能
特征学习
半监督学习
机器学习
正规化(语言学)
理论计算机科学
模式识别(心理学)
作者
Xiao Luo,Wei Ju,Yiyang Gu,Zhengyang Mao,Luchen Liu,Yuhui Yuan,Ming Zhang
出处
期刊:ACM Transactions on Knowledge Discovery From Data
[Association for Computing Machinery]
日期:2023-11-14
卷期号:18 (2): 1-23
被引量:1
摘要
The recently developed unsupervised graph representation learning approaches apply contrastive learning into graph-structured data and achieve promising performance. However, these methods mainly focus on graph augmentation for positive samples, while the negative mining strategies for graph contrastive learning are less explored, leading to sub-optimal performance. To tackle this issue, we propose a Graph Adversarial Contrastive Learning (GraphACL) scheme that learns a bank of negative samples for effective self-supervised whole-graph representation learning. Our GraphACL consists of (i) a graph encoding branch that generates the representations of positive samples and (ii) an adversarial generation branch that produces a bank of negative samples. To generate more powerful hard negative samples, our method minimizes the contrastive loss during encoding updating while maximizing the contrastive loss adversarially over the negative samples for providing the challenging contrastive task. Moreover, the quality of representations produced by the adversarial generation branch is enhanced through the regularization of carefully designed bank divergence loss and bank orthogonality loss. We optimize the parameters of the graph encoding branch and adversarial generation branch alternately. Extensive experiments on 14 real-world benchmarks on both graph classification and transfer learning tasks demonstrate the effectiveness of the proposed approach over existing graph self-supervised representation learning methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI