Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
cs.LG
Submitted: 2026-05-13
Updated: 2026-11-07
Terminology
Sources
- A Survey of Complex-Valued Neural Networks
- A Generalization of Transformer Networks to Graphs
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- TUDataset: A collection of benchmark datasets for learning with graphs
- Graph Unitary Message Passing
- Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing
- Quantum Graph Neural Networks
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis