{"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/neural-causal-abstractions","title":"Neural Causal Abstractions","arxiv_id":"2401.02602","date":"2024-01-05","proceeding":null,"authors":["Kevin Xia","Elias Bareinboim"],"abstract":"The abilities of humans to understand the world in terms of cause and effect relationships, as well as to compress information into abstract concepts, are two hallmark features of human intelligence. These two topics have been studied in tandem in the literature under the rubric of causal abstractions theory. In practice, it remains an open problem how to best leverage abstraction theory in real-world causal inference tasks, where the true mechanisms are unknown and only limited data is available. In this paper, we develop a new family of causal abstractions by clustering variables and their domains. This approach refines and generalizes previous notions of abstractions to better accommodate individual causal distributions that are spawned by Pearl's causal hierarchy. We show that such abstractions are learnable in practical settings through Neural Causal Models (Xia et al., 2021), enabling the use of the deep learning toolkit to solve various challenging causal inference tasks -- identification, estimation, sampling -- at different levels of granularity. Finally, we integrate these results with representation learning to create more flexible abstractions, moving these results closer to practical applications. Our experiments support the theory and illustrate how to scale causal inferences to high-dimensional settings involving image data.","url_abs":"https://arxiv.org/abs/2401.02602v2","url_pdf":"https://arxiv.org/pdf/2401.02602v2.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":"neural-causal-abstractions","repo_url":"https://github.com/causalailab/neuralcausalabstractions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"causal-inference","task_name":"Causal Inference"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"causal-inference","method_name":"Causal inference"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.02602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02602"}},"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/causalailab/neuralcausalabstractions","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/CausalAILab/NeuralCausalAbstractions","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"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":"dd7ca97801804c9b","entry":"convert_to_arrays","repo":"CausalAILab/NeuralCausalAbstractions","repo_kind":"official","path":"src/experiment/experiment1_est_results.py","file_url":"https://github.com/CausalAILab/NeuralCausalAbstractions/blob/HEAD/src/experiment/experiment1_est_results.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":"dd7ca97801804c9b"}},{"code_sha256_prefix":"ff9d4b9593ad1a92","entry":"expand_do","repo":"CausalAILab/NeuralCausalAbstractions","repo_kind":"official","path":"src/datagen/color_mnist.py","file_url":"https://github.com/CausalAILab/NeuralCausalAbstractions/blob/HEAD/src/datagen/color_mnist.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":"ff9d4b9593ad1a92"}},{"code_sha256_prefix":"cf53883c3511b46b","entry":"graph_search","repo":"CausalAILab/NeuralCausalAbstractions","repo_kind":"official","path":"src/ds/causal_graph.py","file_url":"https://github.com/CausalAILab/NeuralCausalAbstractions/blob/HEAD/src/ds/causal_graph.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":"cf53883c3511b46b"}},{"code_sha256_prefix":"3b144fda77dde5b9","entry":"running_average","repo":"CausalAILab/NeuralCausalAbstractions","repo_kind":"official","path":"src/experiment/experiment1_id_results.py","file_url":"https://github.com/CausalAILab/NeuralCausalAbstractions/blob/HEAD/src/experiment/experiment1_id_results.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":"3b144fda77dde5b9"}},{"code_sha256_prefix":"00560aebab89a5aa","entry":"get_transform","repo":"CausalAILab/NeuralCausalAbstractions","repo_kind":"official","path":"src/datagen/img_transforms.py","file_url":"https://github.com/CausalAILab/NeuralCausalAbstractions/blob/HEAD/src/datagen/img_transforms.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":"00560aebab89a5aa"}},{"code_sha256_prefix":"661cfd97bbe3bbb6","entry":"identify","repo":"CausalAILab/NeuralCausalAbstractions","repo_kind":"official","path":"src/ds/symbolic_id_tools.py","file_url":"https://github.com/CausalAILab/NeuralCausalAbstractions/blob/HEAD/src/ds/symbolic_id_tools.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":"661cfd97bbe3bbb6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}