{"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/towards-learning-causal-representations-from","title":"Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization","arxiv_id":"2202.12570","date":"2022-02-25","proceeding":null,"authors":["Weijia Zhang","Xuanhui Zhang","Han-Wen Deng","Min-Ling Zhang"],"abstract":"Multi-instance learning (MIL) deals with objects represented as bags of instances and can predict instance labels from bag-level supervision. However, significant performance gaps exist between instance-level MIL algorithms and supervised learners since the instance labels are unavailable in MIL. Most existing MIL algorithms tackle the problem by treating multi-instance bags as harmful ambiguities and predicting instance labels by reducing the supervision inexactness. This work studies MIL from a new perspective by considering bags as auxiliary information, and utilize it to identify instance-level causal representations from bag-level weak supervision. We propose the CausalMIL algorithm, which not only excels at instance label prediction but also provides robustness to distribution change by synergistically integrating MIL with identifiable variational autoencoder. Our approach is based on a practical and general assumption: the prior distribution over the instance latent representations belongs to the non-factorized exponential family conditioning on the multi-instance bags. Experiments on synthetic and real-world datasets demonstrate that our approach significantly outperforms various baselines on instance label prediction and out-of-distribution generalization tasks.","url_abs":"https://arxiv.org/abs/2202.12570v3","url_pdf":"https://arxiv.org/pdf/2202.12570v3.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":"towards-learning-causal-representations-from","repo_url":"https://github.com/weijiazhang24/causalmil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.12570","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.12570"}},"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/weijiazhang24/causalmil","reach":null}],"summary":{"ran":4,"ran_fixture":1,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":9,"samples":[{"code_sha256_prefix":"d141b7bfe9f6d609","entry":"auxiliary_y_fixed","repo":"weijiazhang24/causalmil","repo_kind":"official","path":"models/networks_colon.py","file_url":"https://github.com/weijiazhang24/causalmil/blob/HEAD/models/networks_colon.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d141b7bfe9f6d609"}},{"code_sha256_prefix":"ecd62e78f2417bca","entry":"decoder_x","repo":"weijiazhang24/causalmil","repo_kind":"official","path":"models/networks_colon.py","file_url":"https://github.com/weijiazhang24/causalmil/blob/HEAD/models/networks_colon.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ecd62e78f2417bca"}},{"code_sha256_prefix":"99c2e0ee30097924","entry":"deep_set_prior","repo":"weijiazhang24/causalmil","repo_kind":"official","path":"models/networks_colon.py","file_url":"https://github.com/weijiazhang24/causalmil/blob/HEAD/models/networks_colon.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"99c2e0ee30097924"}},{"code_sha256_prefix":"8a15fba5642ae1e4","entry":"encoder_x","repo":"weijiazhang24/causalmil","repo_kind":"official","path":"models/networks_colon.py","file_url":"https://github.com/weijiazhang24/causalmil/blob/HEAD/models/networks_colon.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a15fba5642ae1e4"}},{"code_sha256_prefix":"1da6e5ace7827078","entry":"encoder_xnou","repo":"weijiazhang24/causalmil","repo_kind":"official","path":"models/networks_colon.py","file_url":"https://github.com/weijiazhang24/causalmil/blob/HEAD/models/networks_colon.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1da6e5ace7827078"}},{"code_sha256_prefix":"3161bf3db35021c8","entry":"load_dataset","repo":"weijiazhang24/causalmil","repo_kind":"official","path":"colon_cancer.py","file_url":"https://github.com/weijiazhang24/causalmil/blob/HEAD/colon_cancer.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":"3161bf3db35021c8"}},{"code_sha256_prefix":"a8af5d69a10f1fd8","entry":"mi_collate_img","repo":"weijiazhang24/causalmil","repo_kind":"official","path":"colon_cancer.py","file_url":"https://github.com/weijiazhang24/causalmil/blob/HEAD/colon_cancer.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":"a8af5d69a10f1fd8"}},{"code_sha256_prefix":"f32a2c7298ff5a4a","entry":"reorder_y","repo":"weijiazhang24/causalmil","repo_kind":"official","path":"models/networks_colon.py","file_url":"https://github.com/weijiazhang24/causalmil/blob/HEAD/models/networks_colon.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f32a2c7298ff5a4a"}},{"code_sha256_prefix":"1a36b5a138bf3b58","entry":"cmil","repo":"weijiazhang24/causalmil","repo_kind":"official","path":"models/networks_colon.py","file_url":"https://github.com/weijiazhang24/causalmil/blob/HEAD/models/networks_colon.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a36b5a138bf3b58"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}