{"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/boosted-dynamic-neural-networks","title":"Boosted Dynamic Neural Networks","arxiv_id":"2211.16726","date":"2022-11-30","proceeding":null,"authors":["Haichao Yu","Haoxiang Li","Gang Hua","Gao Huang","Humphrey Shi"],"abstract":"Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural networks, has been widely studied recently. A typical EDNN has multiple prediction heads at different layers of the network backbone. During inference, the model will exit at either the last prediction head or an intermediate prediction head where the prediction confidence is higher than a predefined threshold. To optimize the model, these prediction heads together with the network backbone are trained on every batch of training data. This brings a train-test mismatch problem that all the prediction heads are optimized on all types of data in training phase while the deeper heads will only see difficult inputs in testing phase. Treating training and testing inputs differently at the two phases will cause the mismatch between training and testing data distributions. To mitigate this problem, we formulate an EDNN as an additive model inspired by gradient boosting, and propose multiple training techniques to optimize the model effectively. We name our method BoostNet. Our experiments show it achieves the state-of-the-art performance on CIFAR100 and ImageNet datasets in both anytime and budgeted-batch prediction modes. Our code is released at https://github.com/SHI-Labs/Boosted-Dynamic-Networks.","url_abs":"https://arxiv.org/abs/2211.16726v1","url_pdf":"https://arxiv.org/pdf/2211.16726v1.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":"boosted-dynamic-neural-networks","repo_url":"https://github.com/SHI-Labs/Boosted-Dynamic-Networks","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dynamic-neural-networks","task_name":"Dynamic neural networks"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.16726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16726"}},"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/SHI-Labs/Boosted-Dynamic-Networks","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"e26baa07200cad5a","entry":"get_dataloaders","repo":"SHI-Labs/Boosted-Dynamic-Networks","repo_kind":"official","path":"dataloader.py","file_url":"https://github.com/SHI-Labs/Boosted-Dynamic-Networks/blob/HEAD/dataloader.py","link_basis":"harvester_set","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":"e26baa07200cad5a"}},{"code_sha256_prefix":"35a5cf7271901d9c","entry":"get_layer_info","repo":"SHI-Labs/Boosted-Dynamic-Networks","repo_kind":"official","path":"op_counter.py","file_url":"https://github.com/SHI-Labs/Boosted-Dynamic-Networks/blob/HEAD/op_counter.py","link_basis":"harvester_set","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":"35a5cf7271901d9c"}},{"code_sha256_prefix":"76cc74efee42ba21","entry":"get_num_gen","repo":"SHI-Labs/Boosted-Dynamic-Networks","repo_kind":"official","path":"op_counter.py","file_url":"https://github.com/SHI-Labs/Boosted-Dynamic-Networks/blob/HEAD/op_counter.py","link_basis":"harvester_set","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":"76cc74efee42ba21"}},{"code_sha256_prefix":"26ff085b343fa39e","entry":"is_leaf","repo":"SHI-Labs/Boosted-Dynamic-Networks","repo_kind":"official","path":"op_counter.py","file_url":"https://github.com/SHI-Labs/Boosted-Dynamic-Networks/blob/HEAD/op_counter.py","link_basis":"harvester_set","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":"26ff085b343fa39e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}