{"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/caring-learning-temporal-causal","title":"CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process","arxiv_id":"2401.14535","date":"2024-01-25","proceeding":null,"authors":["Guangyi Chen","Yifan Shen","Zhenhao Chen","Xiangchen Song","Yuewen Sun","Weiran Yao","Xiao Liu","Kun Zhang"],"abstract":"Identifying the underlying time-delayed latent causal processes in sequential data is vital for grasping temporal dynamics and making downstream reasoning. While some recent methods can robustly identify these latent causal variables, they rely on strict assumptions about the invertible generation process from latent variables to observed data. However, these assumptions are often hard to satisfy in real-world applications containing information loss. For instance, the visual perception process translates a 3D space into 2D images, or the phenomenon of persistence of vision incorporates historical data into current perceptions. To address this challenge, we establish an identifiability theory that allows for the recovery of independent latent components even when they come from a nonlinear and non-invertible mix. Using this theory as a foundation, we propose a principled approach, CaRiNG, to learn the CAusal RepresentatIon of Non-invertible Generative temporal data with identifiability guarantees. Specifically, we utilize temporal context to recover lost latent information and apply the conditions in our theory to guide the training process. Through experiments conducted on synthetic datasets, we validate that our CaRiNG method reliably identifies the causal process, even when the generation process is non-invertible. Moreover, we demonstrate that our approach considerably improves temporal understanding and reasoning in practical applications.","url_abs":"https://arxiv.org/abs/2401.14535v2","url_pdf":"https://arxiv.org/pdf/2401.14535v2.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":"caring-learning-temporal-causal","repo_url":"https://github.com/sanshuiii/caring","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.14535","atlas_url":"https://app.syntology.ai/?focus=2401.14535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14535"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/sanshuiii/CaRiNG","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sanshuiii/caring","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":10,"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":0,"samples":[{"code_sha256_prefix":"d4fd240849acc2b3","entry":"BetaVAE_MLP","repo":"sanshuiii/caring","repo_kind":"official","path":"caring/modules/stationary.py","file_url":"https://github.com/sanshuiii/caring/blob/HEAD/caring/modules/stationary.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4fd240849acc2b3"}},{"code_sha256_prefix":"773460f058b3b35c","entry":"Inference","repo":"sanshuiii/caring","repo_kind":"official","path":"caring/modules/stationary.py","file_url":"https://github.com/sanshuiii/caring/blob/HEAD/caring/modules/stationary.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":"773460f058b3b35c"}},{"code_sha256_prefix":"d6c09b008d2e8fe3","entry":"MLPDecoder","repo":"sanshuiii/caring","repo_kind":"official","path":"caring/modules/stationary.py","file_url":"https://github.com/sanshuiii/caring/blob/HEAD/caring/modules/stationary.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6c09b008d2e8fe3"}},{"code_sha256_prefix":"bfc5af9d3691e10d","entry":"MLPEncoder","repo":"sanshuiii/caring","repo_kind":"official","path":"caring/modules/stationary.py","file_url":"https://github.com/sanshuiii/caring/blob/HEAD/caring/modules/stationary.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfc5af9d3691e10d"}},{"code_sha256_prefix":"bdecb548777436c9","entry":"NPTransitionPrior","repo":"sanshuiii/caring","repo_kind":"official","path":"caring/modules/stationary.py","file_url":"https://github.com/sanshuiii/caring/blob/HEAD/caring/modules/stationary.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":"bdecb548777436c9"}},{"code_sha256_prefix":"af54234bb8d55554","entry":"concat_x_byx","repo":"sanshuiii/CaRiNG","repo_kind":"official","path":"caring/datasets/checker.py","file_url":"https://github.com/sanshuiii/CaRiNG/blob/HEAD/caring/datasets/checker.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":"af54234bb8d55554"}},{"code_sha256_prefix":"819cc462002cb6c0","entry":"concat_x_byy","repo":"sanshuiii/CaRiNG","repo_kind":"official","path":"caring/datasets/checker.py","file_url":"https://github.com/sanshuiii/CaRiNG/blob/HEAD/caring/datasets/checker.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":"819cc462002cb6c0"}},{"code_sha256_prefix":"863fc64cd51264f0","entry":"reparametrize","repo":"sanshuiii/CaRiNG","repo_kind":"official","path":"caring/modules/components/beta.py","file_url":"https://github.com/sanshuiii/CaRiNG/blob/HEAD/caring/modules/components/beta.py","link_basis":"harvester_set","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":"863fc64cd51264f0"}},{"code_sha256_prefix":"bec6363e2390b390","entry":"StationaryProcess","repo":"sanshuiii/caring","repo_kind":"official","path":"caring/modules/stationary.py","file_url":"https://github.com/sanshuiii/caring/blob/HEAD/caring/modules/stationary.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":"bec6363e2390b390"}},{"code_sha256_prefix":"efb4053bab2aa8c2","entry":"check_lag_byx","repo":"sanshuiii/CaRiNG","repo_kind":"official","path":"caring/datasets/checker.py","file_url":"https://github.com/sanshuiii/CaRiNG/blob/HEAD/caring/datasets/checker.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":"efb4053bab2aa8c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}