Can Graph Learning Learn Circuits?
cs.LG
Submitted: 2026-08-09
Updated: 2026-10-16
Code: https://github.com/graph-learning-circuits/graph-learning-circuits
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Graph Foundation Models: A Comprehensive Survey
- Billion-Scale Graph Foundation Models
- Fast Graph Representation Learning with PyTorch Geometric
- PyG 2.0: Scalable Learning on Real World Graphs
- Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning
- The Hydra Effect: Emergent Self-repair in Language Model Computations
- MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability
- Scalable Circuit Learning for Interpreting Large Language Models
- Discovering Interpretable Algorithms by Decompiling Transformers to RASP
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