CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Sources
- Transfer Learning Between Different Architectures Via Weights Injection
- A Survey of Weight Space Learning: Understanding, Representation, and Generation
- Distilling the Knowledge in a Neural Network
- Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
- Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning
- Predicting Neural Network Accuracy from Weights
- Neural Network Diffusion
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
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