{"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/mixturegrowth-growing-neural-networks-by","title":"MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters","arxiv_id":"2311.04251","date":"2023-11-07","proceeding":null,"authors":["Chau Pham","Piotr Teterwak","Soren Nelson","Bryan A. Plummer"],"abstract":"Most deep neural networks are trained under fixed network architectures and require retraining when the architecture changes. If expanding the network's size is needed, it is necessary to retrain from scratch, which is expensive. To avoid this, one can grow from a small network by adding random weights over time to gradually achieve the target network size. However, this naive approach falls short in practice as it brings too much noise to the growing process. Prior work tackled this issue by leveraging the already learned weights and training data for generating new weights through conducting a computationally expensive analysis step. In this paper, we introduce MixtureGrowth, a new approach to growing networks that circumvents the initialization overhead in prior work. Before growing, each layer in our model is generated with a linear combination of parameter templates. Newly grown layer weights are generated by using a new linear combination of existing templates for a layer. On one hand, these templates are already trained for the task, providing a strong initialization. On the other, the new coefficients provide flexibility for the added layer weights to learn something new. We show that our approach boosts top-1 accuracy over the state-of-the-art by 2-2.5% on CIFAR-100 and ImageNet datasets, while achieving comparable performance with fewer FLOPs to a larger network trained from scratch. Code is available at https://github.com/chaudatascience/mixturegrowth.","url_abs":"https://arxiv.org/abs/2311.04251v1","url_pdf":"https://arxiv.org/pdf/2311.04251v1.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":"mixturegrowth-growing-neural-networks-by","repo_url":"https://github.com/chaudatascience/mixturegrowth","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.04251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04251"}},"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/chaudatascience/mixturegrowth","reach":{"status":"ok"}}],"summary":{"ran":8,"ran_violates":1,"unverified":5},"by_repo_kind":{"official":{"samples":14,"ran":9,"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":14,"samples":[{"code_sha256_prefix":"221b3e9ff9d69ad5","entry":"add_flop_jit","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"compute_flops.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/compute_flops.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"221b3e9ff9d69ad5"}},{"code_sha256_prefix":"76b73ee5dfb47c09","entry":"conv1x1","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"models/normal_wrn.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/models/normal_wrn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"76b73ee5dfb47c09"}},{"code_sha256_prefix":"cbb2fbc77df061cb","entry":"conv3x3","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"models/normal_wrn.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/models/normal_wrn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cbb2fbc77df061cb"}},{"code_sha256_prefix":"3eae384863fd8854","entry":"deeper","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"models/net2net.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/models/net2net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3eae384863fd8854"}},{"code_sha256_prefix":"fc5efb11228c635c","entry":"default","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"utils.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc5efb11228c635c"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"utils.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"242b9981f611e7af","entry":"mul_flop_jit","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"compute_flops.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/compute_flops.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"242b9981f611e7af"}},{"code_sha256_prefix":"26cae4c9fa6d0f84","entry":"normal_wrn_imagenet","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"models/normal_wrn_imagenet.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/models/normal_wrn_imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26cae4c9fa6d0f84"}},{"code_sha256_prefix":"9ebb3080fbba9630","entry":"normalwrn","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"models/normal_wrn.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/models/normal_wrn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ebb3080fbba9630"}},{"code_sha256_prefix":"f2c9e4b934914566","entry":"fast_collate","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"utils.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f2c9e4b934914566"}},{"code_sha256_prefix":"32414bed651601e4","entry":"get_py_logger","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"custom_log.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/custom_log.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32414bed651601e4"}},{"code_sha256_prefix":"f307b29b8c4e63be","entry":"wider","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"models/net2net.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/models/net2net.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f307b29b8c4e63be"}},{"code_sha256_prefix":"93b218cc4cd50f78","entry":"wrn","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"models/template_mixing_wrn_no_bank.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/models/template_mixing_wrn_no_bank.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"93b218cc4cd50f78"}},{"code_sha256_prefix":"79fb86db1e002e02","entry":"wrn_imagenet","repo":"chaudatascience/mixturegrowth","repo_kind":"official","path":"models/template_mixing_wrn_no_bank.py","file_url":"https://github.com/chaudatascience/mixturegrowth/blob/HEAD/models/template_mixing_wrn_no_bank.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"79fb86db1e002e02"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}