{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/graph-neural-networks-for-learning","title":"Graph Neural Networks for Learning Equivariant Representations of Neural Networks","arxiv_id":"2403.12143","date":"2024-03-18","proceeding":null,"authors":["Miltiadis Kofinas","Boris Knyazev","Yan Zhang","Yunlu Chen","Gertjan J. Burghouts","Efstratios Gavves","Cees G. M. Snoek","David W. Zhang"],"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.","url_abs":"https://arxiv.org/abs/2403.12143v3","url_pdf":"https://arxiv.org/pdf/2403.12143v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"graph-neural-networks-for-learning","repo_url":"https://github.com/mkofinas/neural-graphs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.12143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12143"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/mkofinas/neural-graphs","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":6},"by_repo_kind":{"official":{"samples":7,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f6b944f50d3f15ae","entry":"count_parameters","repo":"mkofinas/neural-graphs","repo_kind":"official","path":"experiments/utils.py","file_url":"https://github.com/mkofinas/neural-graphs/blob/HEAD/experiments/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"a411cafe9e1009b8","entry":"get_mgrid","repo":"mkofinas/neural-graphs","repo_kind":"official","path":"experiments/data_nfn.py","file_url":"https://github.com/mkofinas/neural-graphs/blob/HEAD/experiments/data_nfn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a411cafe9e1009b8"}},{"code_sha256_prefix":"c71fdc64870c14e9","entry":"graph_to_wb","repo":"mkofinas/neural-graphs","repo_kind":"official","path":"nn/dense_gnn.py","file_url":"https://github.com/mkofinas/neural-graphs/blob/HEAD/nn/dense_gnn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c71fdc64870c14e9"}},{"code_sha256_prefix":"ad0e9580dae385c1","entry":"graphs_to_batch","repo":"mkofinas/neural-graphs","repo_kind":"official","path":"nn/dense_relational_transformer.py","file_url":"https://github.com/mkofinas/neural-graphs/blob/HEAD/nn/dense_relational_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad0e9580dae385c1"}},{"code_sha256_prefix":"428fbdfc9efa2e55","entry":"make_coordinates","repo":"mkofinas/neural-graphs","repo_kind":"official","path":"experiments/utils.py","file_url":"https://github.com/mkofinas/neural-graphs/blob/HEAD/experiments/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"428fbdfc9efa2e55"}},{"code_sha256_prefix":"d127d7b6cd98eaf2","entry":"state_dict_to_tensors","repo":"mkofinas/neural-graphs","repo_kind":"official","path":"experiments/data_nfn.py","file_url":"https://github.com/mkofinas/neural-graphs/blob/HEAD/experiments/data_nfn.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d127d7b6cd98eaf2"}},{"code_sha256_prefix":"89de1d8986f7d696","entry":"to_pyg_batch","repo":"mkofinas/neural-graphs","repo_kind":"official","path":"nn/dynamic_gnn.py","file_url":"https://github.com/mkofinas/neural-graphs/blob/HEAD/nn/dynamic_gnn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89de1d8986f7d696"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}