{"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/label-free-explainability-for-unsupervised","title":"Label-Free Explainability for Unsupervised Models","arxiv_id":"2203.01928","date":"2022-03-03","proceeding":null,"authors":["Jonathan Crabbé","Mihaela van der Schaar"],"abstract":"Unsupervised black-box models are challenging to interpret. Indeed, most existing explainability methods require labels to select which component(s) of the black-box's output to interpret. In the absence of labels, black-box outputs often are representation vectors whose components do not correspond to any meaningful quantity. Hence, choosing which component(s) to interpret in a label-free unsupervised/self-supervised setting is an important, yet unsolved problem. To bridge this gap in the literature, we introduce two crucial extensions of post-hoc explanation techniques: (1) label-free feature importance and (2) label-free example importance that respectively highlight influential features and training examples for a black-box to construct representations at inference time. We demonstrate that our extensions can be successfully implemented as simple wrappers around many existing feature and example importance methods. We illustrate the utility of our label-free explainability paradigm through a qualitative and quantitative comparison of representation spaces learned by various autoencoders trained on distinct unsupervised tasks.","url_abs":"https://arxiv.org/abs/2203.01928v3","url_pdf":"https://arxiv.org/pdf/2203.01928v3.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":"label-free-explainability-for-unsupervised","repo_url":"https://github.com/vanderschaarlab/label-free-xai","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"label-free-explainability-for-unsupervised","repo_url":"https://github.com/JonathanCrabbe/Label-Free-XAI","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"label-free-explainability-for-unsupervised","repo_url":"https://github.com/vanderschaarlab/mlforhealthlabpub","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.01928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01928"}},"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/vanderschaarlab/label-free-xai","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JonathanCrabbe/Label-Free-XAI","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vanderschaarlab/mlforhealthlabpub","reach":null}],"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":"4cd3b40825e48433","entry":"attribute_auxiliary","repo":"JonathanCrabbe/Label-Free-XAI","repo_kind":"official","path":"src/lfxai/explanations/features.py","file_url":"https://github.com/JonathanCrabbe/Label-Free-XAI/blob/HEAD/src/lfxai/explanations/features.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":"4cd3b40825e48433"}},{"code_sha256_prefix":"11e405e5bf92f485","entry":"attribute_individual_dim","repo":"JonathanCrabbe/Label-Free-XAI","repo_kind":"official","path":"src/lfxai/explanations/features.py","file_url":"https://github.com/JonathanCrabbe/Label-Free-XAI/blob/HEAD/src/lfxai/explanations/features.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":"11e405e5bf92f485"}},{"code_sha256_prefix":"4cb58b9e6f6f6c64","entry":"generate_masks","repo":"JonathanCrabbe/Label-Free-XAI","repo_kind":"official","path":"src/lfxai/utils/feature_attribution.py","file_url":"https://github.com/JonathanCrabbe/Label-Free-XAI/blob/HEAD/src/lfxai/utils/feature_attribution.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":"4cb58b9e6f6f6c64"}},{"code_sha256_prefix":"70ca3a11d654d9f5","entry":"generate_tseries_masks","repo":"JonathanCrabbe/Label-Free-XAI","repo_kind":"official","path":"src/lfxai/utils/feature_attribution.py","file_url":"https://github.com/JonathanCrabbe/Label-Free-XAI/blob/HEAD/src/lfxai/utils/feature_attribution.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":"70ca3a11d654d9f5"}},{"code_sha256_prefix":"a8637ead59d669bf","entry":"linear_annealing","repo":"JonathanCrabbe/Label-Free-XAI","repo_kind":"official","path":"src/lfxai/models/losses.py","file_url":"https://github.com/JonathanCrabbe/Label-Free-XAI/blob/HEAD/src/lfxai/models/losses.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":"a8637ead59d669bf"}},{"code_sha256_prefix":"8f73ed18573e51be","entry":"log_density_gaussian","repo":"JonathanCrabbe/Label-Free-XAI","repo_kind":"official","path":"src/lfxai/models/images.py","file_url":"https://github.com/JonathanCrabbe/Label-Free-XAI/blob/HEAD/src/lfxai/models/images.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":"8f73ed18573e51be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}