{"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/parameter-prediction-for-unseen-deep","title":"Parameter Prediction for Unseen Deep Architectures","arxiv_id":"2110.13100","date":"2021-10-25","proceeding":"NeurIPS 2021 12","authors":["Boris Knyazev","Michal Drozdzal","Graham W. Taylor","Adriana Romero-Soriano"],"abstract":"Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely hand-designed and computationally inefficient. We study if we can use deep learning to directly predict these parameters by exploiting the past knowledge of training other networks. We introduce a large-scale dataset of diverse computational graphs of neural architectures - DeepNets-1M - and use it to explore parameter prediction on CIFAR-10 and ImageNet. By leveraging advances in graph neural networks, we propose a hypernetwork that can predict performant parameters in a single forward pass taking a fraction of a second, even on a CPU. The proposed model achieves surprisingly good performance on unseen and diverse networks. For example, it is able to predict all 24 million parameters of a ResNet-50 achieving a 60% accuracy on CIFAR-10. On ImageNet, top-5 accuracy of some of our networks approaches 50%. Our task along with the model and results can potentially lead to a new, more computationally efficient paradigm of training networks. Our model also learns a strong representation of neural architectures enabling their analysis.","url_abs":"https://arxiv.org/abs/2110.13100v1","url_pdf":"https://arxiv.org/pdf/2110.13100v1.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":"parameter-prediction-for-unseen-deep","repo_url":"https://github.com/facebookresearch/ppuda","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"parameter-prediction","task_name":"Parameter Prediction"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"ggs-nns","method_name":"GGS-NNs"},{"method_slug":"hypernetwork","method_name":"HyperNetwork"}],"datasets_introduced":[{"slug":"deepnets-1m","name":"DeepNets-1M","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/parameter-prediction-on-cifar10","task":"Parameter Prediction","dataset":"CIFAR10","model":"GHN-2","rank_in_archive_order":1,"of":1,"metrics":{"Classification Accuracy (BN-free)":"36.8","Classification Accuracy (Deep)":"60.5","Classification Accuracy (Dense)":"65.8","Classification Accuracy (ID-test)":"66.9","Classification Accuracy (ResNet-50)":"58.6","Classification Accuracy (ViT)":"11.4","Classification Accuracy (Wide)":"64"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.13100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13100"}},"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/ai-med/squeeze_and_excitation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/lucidrains/vit-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/ppuda","reach":null}],"summary":{"ran":1,"ran_draft_wrong":5,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"found_in_text":{"samples":4,"ran":4,"repositories":1},"community":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"04863499199acab0","entry":"AdaptiveTokenSampling","repo":"lucidrains/vit-pytorch","repo_kind":"found_in_text","path":"vit_pytorch/ats_vit.py","file_url":"https://github.com/lucidrains/vit-pytorch/blob/HEAD/vit_pytorch/ats_vit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04863499199acab0"}},{"code_sha256_prefix":"582b2f1aa69315a0","entry":"batched_index_select","repo":"lucidrains/vit-pytorch","repo_kind":"found_in_text","path":"vit_pytorch/ats_vit.py","file_url":"https://github.com/lucidrains/vit-pytorch/blob/HEAD/vit_pytorch/ats_vit.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"582b2f1aa69315a0"}},{"code_sha256_prefix":"97fce54d0fea583d","entry":"find_closest_first","repo":"aria1th/Hypernetwork-MonkeyPatch-Extension","repo_kind":"community","path":"patches/hypernetwork.py","file_url":"https://github.com/aria1th/Hypernetwork-MonkeyPatch-Extension/blob/HEAD/patches/hypernetwork.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"97fce54d0fea583d"}},{"code_sha256_prefix":"a64b4c5c48a91cc8","entry":"list_hypernetworks","repo":"aria1th/Hypernetwork-MonkeyPatch-Extension","repo_kind":"community","path":"patches/hypernetwork.py","file_url":"https://github.com/aria1th/Hypernetwork-MonkeyPatch-Extension/blob/HEAD/patches/hypernetwork.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a64b4c5c48a91cc8"}},{"code_sha256_prefix":"8f3eea58724263db","entry":"log","repo":"lucidrains/vit-pytorch","repo_kind":"found_in_text","path":"vit_pytorch/ats_vit.py","file_url":"https://github.com/lucidrains/vit-pytorch/blob/HEAD/vit_pytorch/ats_vit.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f3eea58724263db"}},{"code_sha256_prefix":"e18c2d8cad8088d3","entry":"sample_gumbel","repo":"lucidrains/vit-pytorch","repo_kind":"found_in_text","path":"vit_pytorch/ats_vit.py","file_url":"https://github.com/lucidrains/vit-pytorch/blob/HEAD/vit_pytorch/ats_vit.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e18c2d8cad8088d3"}},{"code_sha256_prefix":"89ee63fee8534439","entry":"ghn_parallel","repo":"facebookresearch/ppuda","repo_kind":"official","path":"ppuda/ghn/nn.py","file_url":"https://github.com/facebookresearch/ppuda/blob/HEAD/ppuda/ghn/nn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89ee63fee8534439"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}