[SKKU AI Colloquium 2025] 정희수 학생-Rethinking Graph Self-Supervised Learning: Advances, Analyses, and
Автор: 성균관대학교AI대학원
Загружено: 2026-01-11
Просмотров: 24
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.
![[SKKU AI Colloquium 2025] 정희수 학생-Rethinking Graph Self-Supervised Learning: Advances, Analyses, and](https://imager.clipsaver.ru/K9aa35N8HDo/max.jpg)
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
![[SKKU AI Colloquium 2025] 우홍욱 교수-Pathways to AGI : agentic, embodied, physical AI](https://imager.clipsaver.ru/I8gCVWAcfDM/max.jpg)
![[SKKU AI Colloquium 2025] 이진섭 학생-Robust and Generalized Learning in Real-world Scenarios](https://imager.clipsaver.ru/wq-ndT3YYhA/max.jpg)
![[PoD] Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders](https://imager.clipsaver.ru/AeDu1gS6kzQ/max.jpg)
![[SKKU AI Colloquium2025] 심규홍 교수-Context Compression for Efficient Multimodal LLMs](https://imager.clipsaver.ru/ZkoO2nJNC_c/max.jpg)
![[SKKU AI Colloquium 2025] 이선재 교수-GUI Agent: Practical Solutions to automating all digital tasks](https://imager.clipsaver.ru/DBAYZ-fpfTU/max.jpg)
![[SKKU AI Colloquium 2025] 민동문 교수-Quantum Machine Learning: System Architect’s Perspective](https://imager.clipsaver.ru/RWAo7DJXHNo/max.jpg)
![[SKKU AI Colloqium2024] 박은병 교수-Compact 3D Gaussian Representation for Radiance Field](https://imager.clipsaver.ru/ooPSDSNikz4/max.jpg)
![Как происходит модернизация остаточных соединений [mHC]](https://imager.clipsaver.ru/jYn_1PpRzxI/max.jpg)
