Pre-training Graph Neural Networks on 2D and 3D Molecular Structures by using Multi-View Conditional Information Bottleneck

Documenti analoghi

• Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck
  di: Hoang, Van Thuy, et al.
  Pubblicazione: (2024)
• Context-aware Graph Causality Inference for Few-Shot Molecular Property Prediction
  di: Hoang, Van Thuy, et al.
  Pubblicazione: (2026)
• A Survey on Structure-Preserving Graph Transformers
  di: Hoang, Van Thuy, et al.
  Pubblicazione: (2024)
• Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention
  di: Hoang, Van Thuy, et al.
  Pubblicazione: (2025)
• Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks
  di: Zhao, Zhe, et al.
  Pubblicazione: (2024)