Transferable Graph Metanetworks
stat.ML, cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/yuxinma98/transferable-graph-metanetworks
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Graph Meta-Network for Learning on Kolmogorov-Arnold Networks
- A Survey of Weight Space Learning: Understanding, Representation, and Generation
- What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
- Learning Useful Representations of Recurrent Neural Network Weight Matrices
- On Transferring Transferability: Towards a Theory for Size Generalization
- Equivariant Deep Weight Space Alignment
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Predicting Neural Network Accuracy from Weights
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier