.png){kind=icon}
.png){kind=icon}
Return
SE-GSSL: Soft-Mask enhanced graph self-supervised learning with multi-aspect knowledge encoding and adaptive sample selection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2025.114048.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph self-supervised learning (GSSL) has garnered significant attention owing to its powerful expressive capabilities. It learns from unlabeled graph data through pretext tasks, such as AttributeMask, S 2GRL, and GZL. However, most existing methods face challenges when performing these pretext tasks: (1) The model tends to select nodes whose features are easy to predict, resulting in the learned information being too simple and lacking actual semantic value. (2) The noise in node features can mislead the model to learn wrong information, which can easily lead to over-fitting and reduce generalization ability. To address these limitations, we propose a novel GSSL framework termed Selection-Enhanced GSSL (SE-GSSL), which integrates sample selection into the learning paradigm. Furthermore, we introduce an end-to-end Soft-Mask-based SE-GSSL framework as a concrete implementation. First, we design multiple individual encoders to extract differentiated knowledge of node features and graph topology, and achieve complementary enhancement in fusion. Second, a multi-head global projection matrix with diversity regularization is presented to calculate the scores for all nodes to enhance the evaluation of node importance. Third, a new masking strategy called Soft-Mask is proposed to mask nodes, which can adaptively adjust the difficulties of different self-supervised reconstruction tasks. Finally, extensive experiments on various public graph benchmarks demonstrate that the proposed framework can achieve better or at least competitive performance compared to many other baselines or recent state-of-the-art methods in semi-supervised node classification and node clustering tasks.
Journal
K
IF:
7.6
Papers:
1.2W
Citations:
4.5W
Organization
No organization information available