Edge-Level Automorphism in GNNs: A Quantitative Framework and Effective Designs For Link Prediction
cs.LG, cs.GT
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/tkipf/gcn
Terminology
Sources
- Fast Graph Representation Learning with PyTorch Geometric
- Improving neural networks by preventing co-adaptation of feature detectors
- Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction
- Understanding Generalization in Node and Link Prediction
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks