时间：2025-11-12
本文（Conditional distribution learning for graph classification）原载Proceedings of the AAAI Conference on Artificial Intelligence，由四川大学王竹教授等科研人员创作，系四川大学市场经济法治研究所系列学术成果。后续会持续分享四川大学市场经济法治研究所系列学术成果，欢迎大家阅读。
Graph contrastive learning (GCL) has shown
promising performance in semisupervised graph classification.
However, existing studies still encounter significant challenges in
GCL. First, successive layers in graph neural network (GNN)
tend to produce more similar node embeddings, while GCL
aims to increase the dissimilarity between negative pairs of
node embeddings. This inevitably results in a conflict between
the message-passing mechanism of GNNs and the contrastive
learning of negative pairs via intraviews. Second, leveraging the
diversity and quantity of data provided by graph-structured data
augmentations while preserving intrinsic semantic information
is challenging. In this paper, we propose a self-supervised
conditional distribution learning (SSCDL) method designed to
learn graph representations from graph-structured data for
semisupervised graph classification. Specifically, we present an
end-to-end graph representation learning model to align the
conditional distributions of weakly and strongly augmented
features over the original features. This alignment effectively
reduces the risk of disrupting intrinsic semantic information
through graph-structured data augmentation. To avoid conflict
between the message-passing mechanism and contrastive learning
of negative pairs, positive pairs of node representations are re
tained for measuring the similarity between the original features
and the corresponding weakly augmented features. Extensive
experiments with several benchmark graph datasets demonstrate
the effectiveness of the proposed SSCDL method.
Jie Chen, Hua Mao, Chuanbin Liu, Zhu Wang, and Xi Peng. Conditional distribution learning for graph classification. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 40, No. 24: AAAI-26 Technical Tracks 24. （论文下载）
