{"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/multi-view-causal-representation-learning","title":"Multi-View Causal Representation Learning with Partial Observability","arxiv_id":"2311.04056","date":"2023-11-07","proceeding":null,"authors":["Dingling Yao","Danru Xu","Sébastien Lachapelle","Sara Magliacane","Perouz Taslakian","Georg Martius","Julius von Kügelgen","Francesco Locatello"],"abstract":"We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a nonlinear mixture of a subset of underlying latent variables, which can be causally related. We prove that the information shared across all subsets of any number of views can be learned up to a smooth bijection using contrastive learning and a single encoder per view. We also provide graphical criteria indicating which latent variables can be identified through a simple set of rules, which we refer to as identifiability algebra. Our general framework and theoretical results unify and extend several previous works on multi-view nonlinear ICA, disentanglement, and causal representation learning. We experimentally validate our claims on numerical, image, and multi-modal data sets. Further, we demonstrate that the performance of prior methods is recovered in different special cases of our setup. Overall, we find that access to multiple partial views enables us to identify a more fine-grained representation, under the generally milder assumption of partial observability.","url_abs":"https://arxiv.org/abs/2311.04056v2","url_pdf":"https://arxiv.org/pdf/2311.04056v2.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":"multi-view-causal-representation-learning","repo_url":"https://github.com/causallearningai/multiview-crl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-view-causal-representation-learning","repo_url":"https://github.com/simonbing/crlsanitycheck","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"ica","method_name":"ICA"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.04056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04056"}},"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/causallearningai/multiview-crl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simonbing/crlsanitycheck","reach":null}],"summary":{"ran":5,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":5,"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":"170d8b2c7bff0cd3","entry":"compute_importance_gbt","repo":"causallearningai/multiview-crl","repo_kind":"official","path":"dci.py","file_url":"https://github.com/causallearningai/multiview-crl/blob/HEAD/dci.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"170d8b2c7bff0cd3"}},{"code_sha256_prefix":"3ccb71a3d6deb62b","entry":"construct_invertible_mlp","repo":"causallearningai/multiview-crl","repo_kind":"official","path":"invertible_network_utils.py","file_url":"https://github.com/causallearningai/multiview-crl/blob/HEAD/invertible_network_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ccb71a3d6deb62b"}},{"code_sha256_prefix":"f029699ecdd0a5b1","entry":"get_mlp","repo":"causallearningai/multiview-crl","repo_kind":"official","path":"encoders.py","file_url":"https://github.com/causallearningai/multiview-crl/blob/HEAD/encoders.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f029699ecdd0a5b1"}},{"code_sha256_prefix":"99a88e5f37a92f0d","entry":"powerset","repo":"causallearningai/multiview-crl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/causallearningai/multiview-crl/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99a88e5f37a92f0d"}},{"code_sha256_prefix":"d02c1502ca1f036a","entry":"retrieve_content_style","repo":"causallearningai/multiview-crl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/causallearningai/multiview-crl/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d02c1502ca1f036a"}},{"code_sha256_prefix":"6ddacf82b281e161","entry":"compute_gt_idx","repo":"causallearningai/multiview-crl","repo_kind":"official","path":"main_multimodal.py","file_url":"https://github.com/causallearningai/multiview-crl/blob/HEAD/main_multimodal.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":"6ddacf82b281e161"}},{"code_sha256_prefix":"fa37808e505554e0","entry":"content_style_from_subsets","repo":"causallearningai/multiview-crl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/causallearningai/multiview-crl/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":"fa37808e505554e0"}},{"code_sha256_prefix":"c777641e597bbeab","entry":"infonce_base_loss","repo":"causallearningai/multiview-crl","repo_kind":"official","path":"losses.py","file_url":"https://github.com/causallearningai/multiview-crl/blob/HEAD/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":"c777641e597bbeab"}},{"code_sha256_prefix":"9d41b2149e408698","entry":"infonce_loss","repo":"causallearningai/multiview-crl","repo_kind":"official","path":"losses.py","file_url":"https://github.com/causallearningai/multiview-crl/blob/HEAD/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":"9d41b2149e408698"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}