[SKKU AI Colloquium 2025] 정희수 학생-Rethinking Graph Self-Supervised Learning: Advances, Analyses, and скачать в хорошем качестве

[SKKU AI Colloquium 2025] 정희수 학생-Rethinking Graph Self-Supervised Learning: Advances, Analyses, and

발표제목: Rethinking Graph Self-Supervised Learning: Advances, Analyses, and Explanations 발표자: 정희수 학생 발표요약: This work examines graph self-supervised learning (SSL) by integrating three complementary advances in methodology, theoretical understanding, and explainability. CIMAGE refines masked graph auto-encoding through a conditional–independence–guided masking strategy that reduces redundancy and enhances the relevance of reconstructed signals, yielding linearly separable and robust representations. BSG provides an information-theoretic decomposition of graph SSL objectives, analyzes the role of embedding smoothness in shaping model performance, and introduces a balanced loss that reconciles competing smoothness effects across diverse tasks. HINT-G extends the scope of GNN explanation for SSL by leveraging influence functions to identify both existing and non-existent edges that significantly shape learned representations, enabling task-agnostic explanations. Together, these contributions offer a unified perspective on the mechanisms, trade-offs, and explanatory principles of graph self-supervised learning.