{"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/selective-mixup-fine-tuning-for-optimizing","title":"Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives","arxiv_id":"2403.18301","date":"2024-03-27","proceeding":null,"authors":["Shrinivas Ramasubramanian","Harsh Rangwani","Sho Takemori","Kunal Samanta","Yuhei Umeda","Venkatesh Babu Radhakrishnan"],"abstract":"The rise in internet usage has led to the generation of massive amounts of data, resulting in the adoption of various supervised and semi-supervised machine learning algorithms, which can effectively utilize the colossal amount of data to train models. However, before deploying these models in the real world, these must be strictly evaluated on performance measures like worst-case recall and satisfy constraints such as fairness. We find that current state-of-the-art empirical techniques offer sub-optimal performance on these practical, non-decomposable performance objectives. On the other hand, the theoretical techniques necessitate training a new model from scratch for each performance objective. To bridge the gap, we propose SelMix, a selective mixup-based inexpensive fine-tuning technique for pre-trained models, to optimize for the desired objective. The core idea of our framework is to determine a sampling distribution to perform a mixup of features between samples from particular classes such that it optimizes the given objective. We comprehensively evaluate our technique against the existing empirical and theoretically principled methods on standard benchmark datasets for imbalanced classification. We find that proposed SelMix fine-tuning significantly improves the performance for various practical non-decomposable objectives across benchmarks.","url_abs":"https://arxiv.org/abs/2403.18301v1","url_pdf":"https://arxiv.org/pdf/2403.18301v1.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":"selective-mixup-fine-tuning-for-optimizing","repo_url":"https://github.com/val-iisc/selmix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"imbalanced-classification","task_name":"imbalanced classification"}],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.18301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18301"}},"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/val-iisc/selmix","reach":null}],"summary":{"ran":2,"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"cd34509ca97cbddb","entry":"FastJointSampler","repo":"val-iisc/selmix","repo_kind":"official","path":"finetuning/selmix_ssl.py","file_url":"https://github.com/val-iisc/selmix/blob/HEAD/finetuning/selmix_ssl.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":"cd34509ca97cbddb"}},{"code_sha256_prefix":"60cd13659fa29f0b","entry":"IndexDataset","repo":"val-iisc/selmix","repo_kind":"official","path":"finetuning/selmix_ssl.py","file_url":"https://github.com/val-iisc/selmix/blob/HEAD/finetuning/selmix_ssl.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":"60cd13659fa29f0b"}},{"code_sha256_prefix":"3a1fe680a5675103","entry":"auc_m","repo":"val-iisc/selmix","repo_kind":"official","path":"finetuning/selmix_ssl.py","file_url":"https://github.com/val-iisc/selmix/blob/HEAD/finetuning/selmix_ssl.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a1fe680a5675103"}},{"code_sha256_prefix":"efc9682fffe68450","entry":"get_metrics","repo":"val-iisc/selmix","repo_kind":"official","path":"finetuning/selmix_ssl.py","file_url":"https://github.com/val-iisc/selmix/blob/HEAD/finetuning/selmix_ssl.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"efc9682fffe68450"}},{"code_sha256_prefix":"95ff8d20c948fe17","entry":"SelMixSSL","repo":"val-iisc/selmix","repo_kind":"official","path":"finetuning/selmix_ssl.py","file_url":"https://github.com/val-iisc/selmix/blob/HEAD/finetuning/selmix_ssl.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":"95ff8d20c948fe17"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}