{"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/provable-concept-learning-for-interpretable","title":"Provable concept learning for interpretable predictions using variational autoencoders","arxiv_id":"2204.00492","date":"2022-04-01","proceeding":null,"authors":["Armeen Taeb","Nicolo Ruggeri","Carina Schnuck","Fanny Yang"],"abstract":"In safety-critical applications, practitioners are reluctant to trust neural networks when no interpretable explanations are available. Many attempts to provide such explanations revolve around pixel-based attributions or use previously known concepts. In this paper we aim to provide explanations by provably identifying \\emph{high-level, previously unknown ground-truth concepts}. To this end, we propose a probabilistic modeling framework to derive (C)oncept (L)earning and (P)rediction (CLAP) -- a VAE-based classifier that uses visually interpretable concepts as predictors for a simple classifier. Assuming a generative model for the ground-truth concepts, we prove that CLAP is able to identify them while attaining optimal classification accuracy. Our experiments on synthetic datasets verify that CLAP identifies distinct ground-truth concepts on synthetic datasets and yields promising results on the medical Chest X-Ray dataset.","url_abs":"https://arxiv.org/abs/2204.00492v3","url_pdf":"https://arxiv.org/pdf/2204.00492v3.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":"provable-concept-learning-for-interpretable","repo_url":"https://github.com/nickruggeri/clap-interpretable-predictions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"provable-concept-learning-for-interpretable","repo_url":"https://github.com/nikruggeri/clap-interpretable-predictions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.00492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.00492"}},"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/nickruggeri/clap-interpretable-predictions","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nikruggeri/clap-interpretable-predictions","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"ran":1,"repositories":2}},"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":"0dbd6c20ab4dfa96","entry":"logits_to_labels","repo":"nickruggeri/clap-interpretable-predictions","repo_kind":"official","path":"src/architecture/clap.py","file_url":"https://github.com/nickruggeri/clap-interpretable-predictions/blob/HEAD/src/architecture/clap.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0dbd6c20ab4dfa96"}},{"code_sha256_prefix":"5370bc15040ed909","entry":"accuracy","repo":"nikruggeri/clap-interpretable-predictions","repo_kind":"official","path":"src/losses.py","file_url":"https://github.com/nikruggeri/clap-interpretable-predictions/blob/HEAD/src/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":"5370bc15040ed909"}},{"code_sha256_prefix":"af02cfe36b2295c3","entry":"bernoulli_reconstruction_loss","repo":"nikruggeri/clap-interpretable-predictions","repo_kind":"official","path":"src/losses.py","file_url":"https://github.com/nikruggeri/clap-interpretable-predictions/blob/HEAD/src/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":"af02cfe36b2295c3"}},{"code_sha256_prefix":"72fe41c708e9ee5a","entry":"cycle_params","repo":"nikruggeri/clap-interpretable-predictions","repo_kind":"official","path":"src/trainer.py","file_url":"https://github.com/nikruggeri/clap-interpretable-predictions/blob/HEAD/src/trainer.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":"72fe41c708e9ee5a"}},{"code_sha256_prefix":"5b9bd96b909d1944","entry":"frange_cycle_linear","repo":"nikruggeri/clap-interpretable-predictions","repo_kind":"official","path":"src/trainer.py","file_url":"https://github.com/nikruggeri/clap-interpretable-predictions/blob/HEAD/src/trainer.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":"5b9bd96b909d1944"}},{"code_sha256_prefix":"ab5aa52c2597d0d8","entry":"latent_kl_divergence","repo":"nikruggeri/clap-interpretable-predictions","repo_kind":"official","path":"src/losses.py","file_url":"https://github.com/nikruggeri/clap-interpretable-predictions/blob/HEAD/src/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":"ab5aa52c2597d0d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}