{"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/desiderata-for-representation-learning-a","title":"Desiderata for Representation Learning: A Causal Perspective","arxiv_id":"2109.03795","date":"2021-09-08","proceeding":null,"authors":["Yixin Wang","Michael I. Jordan"],"abstract":"Representation learning constructs low-dimensional representations to summarize essential features of high-dimensional data. This learning problem is often approached by describing various desiderata associated with learned representations; e.g., that they be non-spurious, efficient, or disentangled. It can be challenging, however, to turn these intuitive desiderata into formal criteria that can be measured and enhanced based on observed data. In this paper, we take a causal perspective on representation learning, formalizing non-spuriousness and efficiency (in supervised representation learning) and disentanglement (in unsupervised representation learning) using counterfactual quantities and observable consequences of causal assertions. This yields computable metrics that can be used to assess the degree to which representations satisfy the desiderata of interest and learn non-spurious and disentangled representations from single observational datasets.","url_abs":"https://arxiv.org/abs/2109.03795v2","url_pdf":"https://arxiv.org/pdf/2109.03795v2.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":"desiderata-for-representation-learning-a","repo_url":"https://github.com/yixinwang/representation-causal-public","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.03795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03795"}},"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/yixinwang/representation-causal-public","reach":null}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"ran_honours":1,"ran_violates":1,"unverified":1},"by_repo_kind":{"listed":{"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":0,"samples":[{"code_sha256_prefix":"7871098faa3e751e","entry":"classical_vae_loss_function","repo":"yixinwang/representation-causal-public","repo_kind":"listed","path":"disentanglement_expms/sec3-4-ioss_vae/src/disentangle_learn.py","file_url":"https://github.com/yixinwang/representation-causal-public/blob/HEAD/disentanglement_expms/sec3-4-ioss_vae/src/disentangle_learn.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":"7871098faa3e751e"}},{"code_sha256_prefix":"2905c704064d6f95","entry":"cond_pns","repo":"yixinwang/representation-causal-public","repo_kind":"listed","path":"causalrep_expms/sec2-4-1-pns_distinguish/src/pns_distinguish.py","file_url":"https://github.com/yixinwang/representation-causal-public/blob/HEAD/causalrep_expms/sec2-4-1-pns_distinguish/src/pns_distinguish.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2905c704064d6f95"}},{"code_sha256_prefix":"c8fd3bb95d7b563e","entry":"pn","repo":"yixinwang/representation-causal-public","repo_kind":"listed","path":"causalrep_expms/sec2-4-1-pns_distinguish/src/pns_distinguish.py","file_url":"https://github.com/yixinwang/representation-causal-public/blob/HEAD/causalrep_expms/sec2-4-1-pns_distinguish/src/pns_distinguish.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":"c8fd3bb95d7b563e"}},{"code_sha256_prefix":"5300aacb60f04fe1","entry":"pns","repo":"yixinwang/representation-causal-public","repo_kind":"listed","path":"causalrep_expms/sec2-4-1-pns_distinguish/src/pns_distinguish.py","file_url":"https://github.com/yixinwang/representation-causal-public/blob/HEAD/causalrep_expms/sec2-4-1-pns_distinguish/src/pns_distinguish.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5300aacb60f04fe1"}},{"code_sha256_prefix":"72788e0afcbe4539","entry":"IOSS","repo":"yixinwang/representation-causal-public","repo_kind":"listed","path":"disentanglement_expms/sec3-4-ioss_vae/src/disentangle_learn.py","file_url":"https://github.com/yixinwang/representation-causal-public/blob/HEAD/disentanglement_expms/sec3-4-ioss_vae/src/disentangle_learn.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":"72788e0afcbe4539"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}