{"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/accelerating-training-with-neuron-interaction","title":"Accelerating Training with Neuron Interaction and Nowcasting Networks","arxiv_id":"2409.04434","date":"2024-09-06","proceeding":null,"authors":["Boris Knyazev","Abhinav Moudgil","Guillaume Lajoie","Eugene Belilovsky","Simon Lacoste-Julien"],"abstract":"Neural network training can be accelerated when a learnable update rule is used in lieu of classic adaptive optimizers (e.g. Adam). However, learnable update rules can be costly and unstable to train and use. Recently, Jang et al. (2023) proposed a simpler approach to accelerate training based on weight nowcaster networks (WNNs). In their approach, Adam is used for most of the optimization steps and periodically, only every few steps, a WNN nowcasts (predicts near future) parameters. We improve WNNs by proposing neuron interaction and nowcasting (NiNo) networks. In contrast to WNNs, NiNo leverages neuron connectivity and graph neural networks to more accurately nowcast parameters. We further show that in some networks, such as Transformers, modeling neuron connectivity accurately is challenging. We address this and other limitations, which allows NiNo to accelerate Adam training by up to 50% in vision and language tasks.","url_abs":"https://arxiv.org/abs/2409.04434v2","url_pdf":"https://arxiv.org/pdf/2409.04434v2.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":"accelerating-training-with-neuron-interaction","repo_url":"https://github.com/samsungsailmontreal/nino","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.04434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04434"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/samsungsailmontreal/nino","reach":null}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":"5274257eb33e5408","entry":"EdgeMLP","repo":"samsungsailmontreal/nino","repo_kind":"official","path":"optim/nino.py","file_url":"https://github.com/samsungsailmontreal/nino/blob/HEAD/optim/nino.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5274257eb33e5408"}},{"code_sha256_prefix":"680f498e65d3b2da","entry":"MLP","repo":"samsungsailmontreal/nino","repo_kind":"official","path":"optim/nino.py","file_url":"https://github.com/samsungsailmontreal/nino/blob/HEAD/optim/nino.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"680f498e65d3b2da"}},{"code_sha256_prefix":"9f17a5e0c5f927ac","entry":"test","repo":"samsungsailmontreal/nino","repo_kind":"official","path":"train_vision.py","file_url":"https://github.com/samsungsailmontreal/nino/blob/HEAD/train_vision.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f17a5e0c5f927ac"}},{"code_sha256_prefix":"92deafb9b889ae70","entry":"NiNo","repo":"samsungsailmontreal/nino","repo_kind":"official","path":"optim/nino.py","file_url":"https://github.com/samsungsailmontreal/nino/blob/HEAD/optim/nino.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92deafb9b889ae70"}},{"code_sha256_prefix":"3937d6b9c027ef1e","entry":"NiNoModel","repo":"samsungsailmontreal/nino","repo_kind":"official","path":"optim/nino.py","file_url":"https://github.com/samsungsailmontreal/nino/blob/HEAD/optim/nino.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3937d6b9c027ef1e"}},{"code_sha256_prefix":"a309fb0999e41b64","entry":"PNA","repo":"samsungsailmontreal/nino","repo_kind":"official","path":"optim/nino.py","file_url":"https://github.com/samsungsailmontreal/nino/blob/HEAD/optim/nino.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a309fb0999e41b64"}},{"code_sha256_prefix":"ad628f616981f9be","entry":"PNAConv","repo":"samsungsailmontreal/nino","repo_kind":"official","path":"optim/nino.py","file_url":"https://github.com/samsungsailmontreal/nino/blob/HEAD/optim/nino.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad628f616981f9be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}