Pith. sign in

REVIEW 4 cited by

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.12143 v3 pith:TVTOQQ5K submitted 2024-03-18 cs.LG cs.AIstat.ML

Miltiadis Kofinas , Boris Knyazev , Yan Zhang , Yunlu Chen , Gertjan J. Burghouts , Efstratios Gavves , Cees G. M. Snoek , David W. Zhang This is my paper · ORCID
classification cs.LGcs.AIstat.ML
keywords neuralnetworksnetworkrepresentationscomputationaldiversegeneralizationgraph
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Neural networks that process the parameters of other neural networks find applications in domains as diverse as classifying implicit neural representations, generating neural network weights, and predicting generalization errors. However, existing approaches either overlook the inherent permutation symmetry in the neural network or rely on intricate weight-sharing patterns to achieve equivariance, while ignoring the impact of the network architecture itself. In this work, we propose to represent neural networks as computational graphs of parameters, which allows us to harness powerful graph neural networks and transformers that preserve permutation symmetry. Consequently, our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations, predicting generalization performance, and learning to optimize, while consistently outperforming state-of-the-art methods. The source code is open-sourced at https://github.com/mkofinas/neural-graphs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. On the Expressive Power of Permutation-Equivariant Weight-Space Networks

    cs.LG 2026-02 conditional novelty 7.0 of 10

    Permutation-equivariant weight-space networks are all equally expressive, and universality holds when hidden-layer biases are pairwise distinct.

  2. Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights

    cs.LG 2025-02 conditional novelty 7.0 of 10

    ProbeLog represents each classifier output by its responses to fixed probe images and uses CLIP to answer text queries, achieving 43.8% top-1 accuracy when searching 1,500 ImageNet-trained models for a concept.

  3. Approximate Energy-Integration Method for Identifying Collisional Neutrino Flavor Instabilities

    astro-ph.HE 2026-04 accept novelty 6.0 of 10

    A sector-wise energy-integration approximation (method C) robustly reduces multi-energy collisional neutrino flavor dispersion relations while matching exact growth rates and frequencies across isotropic, anisotropic,...

  4. Deep Active Inference Agents for Delayed and Long-Horizon Environments

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A policy-conditional world model trained under active inference enables single-lookahead planning over hundreds of steps and beats a DQN baseline on energy-efficient control of parallel machines.

Pith tools