{"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/representation-reliability-and-its-impact-on","title":"Quantifying Representation Reliability in Self-Supervised Learning Models","arxiv_id":"2306.00206","date":"2023-05-31","proceeding":null,"authors":["Young-Jin Park","Hao Wang","Shervin Ardeshir","Navid Azizan"],"abstract":"Self-supervised learning models extract general-purpose representations from data. Quantifying the reliability of these representations is crucial, as many downstream models rely on them as input for their own tasks. To this end, we introduce a formal definition of representation reliability: the representation for a given test point is considered to be reliable if the downstream models built on top of that representation can consistently generate accurate predictions for that test point. However, accessing downstream data to quantify the representation reliability is often infeasible or restricted due to privacy concerns. We propose an ensemble-based method for estimating the representation reliability without knowing the downstream tasks a priori. Our method is based on the concept of neighborhood consistency across distinct pre-trained representation spaces. The key insight is to find shared neighboring points as anchors to align these representation spaces before comparing them. We demonstrate through comprehensive numerical experiments that our method effectively captures the representation reliability with a high degree of correlation, achieving robust and favorable performance compared with baseline methods.","url_abs":"https://arxiv.org/abs/2306.00206v2","url_pdf":"https://arxiv.org/pdf/2306.00206v2.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":"representation-reliability-and-its-impact-on","repo_url":"https://github.com/azizanlab/repreli","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2306.00206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00206"}},"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/azizanlab/repreli","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"192f7fe3c285099d","entry":"batch_cosine_distances","repo":"azizanlab/repreli","repo_kind":"official","path":"utils.py","file_url":"https://github.com/azizanlab/repreli/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"192f7fe3c285099d"}},{"code_sha256_prefix":"dc09c42ce7fc43e5","entry":"batch_euclidean_distances","repo":"azizanlab/repreli","repo_kind":"official","path":"utils.py","file_url":"https://github.com/azizanlab/repreli/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc09c42ce7fc43e5"}},{"code_sha256_prefix":"ac1e04b23ac48896","entry":"fastSort","repo":"azizanlab/repreli","repo_kind":"official","path":"utils.py","file_url":"https://github.com/azizanlab/repreli/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac1e04b23ac48896"}},{"code_sha256_prefix":"0bb63a4bad51d046","entry":"sample_vMF","repo":"azizanlab/repreli","repo_kind":"official","path":"vonMF/util.py","file_url":"https://github.com/azizanlab/repreli/blob/HEAD/vonMF/util.py","link_basis":"first_harvest_node","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":"0bb63a4bad51d046"}},{"code_sha256_prefix":"4825fb6ee1c1e590","entry":"sparse2coarse","repo":"azizanlab/repreli","repo_kind":"official","path":"tasks/cifar100_utils.py","file_url":"https://github.com/azizanlab/repreli/blob/HEAD/tasks/cifar100_utils.py","link_basis":"first_harvest_node","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":"4825fb6ee1c1e590"}},{"code_sha256_prefix":"074a94094f77a2c0","entry":"spherical_k_means","repo":"azizanlab/repreli","repo_kind":"official","path":"vonMF/spherical_kmeans.py","file_url":"https://github.com/azizanlab/repreli/blob/HEAD/vonMF/spherical_kmeans.py","link_basis":"first_harvest_node","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":"074a94094f77a2c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}