{"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/improving-the-efficiency-of-self-supervised","title":"Improving the Efficiency of Self-Supervised Adversarial Training through Latent Clustering-Based Selection","arxiv_id":"2501.10466","date":"2025-01-15","proceeding":null,"authors":["Somrita Ghosh","Yuelin Xu","Xiao Zhang"],"abstract":"Compared with standard learning, adversarially robust learning is widely recognized to demand significantly more training examples. Recent works propose the use of self-supervised adversarial training (SSAT) with external or synthetically generated unlabeled data to enhance model robustness. However, SSAT requires a substantial amount of extra unlabeled data, significantly increasing memory usage and model training times. To address these challenges, we propose novel methods to strategically select a small subset of unlabeled data essential for SSAT and robustness improvement. Our selection prioritizes data points near the model's decision boundary based on latent clustering-based techniques, efficiently identifying a critical subset of unlabeled data with a higher concentration of boundary-adjacent points. While focusing on near-boundary data, our methods are designed to maintain a balanced ratio between boundary and non-boundary data points to avoid overfitting. Our experiments on image benchmarks show that integrating our selection strategies into self-supervised adversarial training can largely reduce memory and computational requirements while achieving high model robustness. In particular, our latent clustering-based selection method with k-means is the most effective, achieving nearly identical test-time robust accuracies with 5 to 10 times less external or generated unlabeled data when applied to image benchmarks. Additionally, we validate the generalizability of our approach across various application scenarios, including a real-world medical dataset for COVID-19 chest X-ray classification.","url_abs":"https://arxiv.org/abs/2501.10466v1","url_pdf":"https://arxiv.org/pdf/2501.10466v1.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":"improving-the-efficiency-of-self-supervised","repo_url":"https://github.com/somrita99/SSATwithLCS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"x-ray-classification","task_name":"X-ray Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.10466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.10466"}},"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/TrustMLRG/EfficientSSAT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/somrita99/SSATwithLCS","reach":null}],"summary":{"ran_draft_wrong":4,"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"found_in_text":{"samples":4,"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":1,"samples":[{"code_sha256_prefix":"906802529bac67d1","entry":"_lcs_km_order","repo":"TrustMLRG/EfficientSSAT","repo_kind":"found_in_text","path":"datasets.py","file_url":"https://github.com/TrustMLRG/EfficientSSAT/blob/HEAD/datasets.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":"906802529bac67d1"}},{"code_sha256_prefix":"3e625fc5f22175b7","entry":"build_embeddings_and_pseudolabels","repo":"somrita99/SSATwithLCS","repo_kind":"official","path":"diffusionmgmm.py","file_url":"https://github.com/somrita99/SSATwithLCS/blob/HEAD/diffusionmgmm.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":"3e625fc5f22175b7"}},{"code_sha256_prefix":"c1621b9c5bab6107","entry":"confidence_minimization_loss","repo":"trustmlrg/efficientssat","repo_kind":"found_in_text","path":"diffusionm.py","file_url":"https://github.com/trustmlrg/efficientssat/blob/HEAD/diffusionm.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":"c1621b9c5bab6107"}},{"code_sha256_prefix":"996b377efc034323","entry":"eval_loader","repo":"trustmlrg/efficientssat","repo_kind":"found_in_text","path":"trainnew.py","file_url":"https://github.com/trustmlrg/efficientssat/blob/HEAD/trainnew.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"996b377efc034323"}},{"code_sha256_prefix":"a13f74ed9b3d0b95","entry":"pgd_linf","repo":"trustmlrg/efficientssat","repo_kind":"found_in_text","path":"pgd_attack.py","file_url":"https://github.com/trustmlrg/efficientssat/blob/HEAD/pgd_attack.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a13f74ed9b3d0b95"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}