{"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/provable-compositional-generalization-for","title":"Provable Compositional Generalization for Object-Centric Learning","arxiv_id":"2310.05327","date":"2023-10-09","proceeding":null,"authors":["Thaddäus Wiedemer","Jack Brady","Alexander Panfilov","Attila Juhos","Matthias Bethge","Wieland Brendel"],"abstract":"Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learning object-centric representations, which are widely conjectured to enable compositional generalization. Yet, it remains unclear when this conjecture will be true, as a principled theoretical or empirical understanding of compositional generalization is lacking. In this work, we investigate when compositional generalization is guaranteed for object-centric representations through the lens of identifiability theory. We show that autoencoders that satisfy structural assumptions on the decoder and enforce encoder-decoder consistency will learn object-centric representations that provably generalize compositionally. We validate our theoretical result and highlight the practical relevance of our assumptions through experiments on synthetic image data.","url_abs":"https://arxiv.org/abs/2310.05327v2","url_pdf":"https://arxiv.org/pdf/2310.05327v2.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":"provable-compositional-generalization-for","repo_url":"https://github.com/brendel-group/objects-compositional-generalization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.05327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05327"}},"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":"deterministic:regex_extraction","url":"https://github.com/brendel-group/objects-compositional-generalization","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"7d33f028f090984d","entry":"collate_fn_normalizer","repo":"brendel-group/objects-compositional-generalization","repo_kind":"official","path":"src/datasets/utils.py","file_url":"https://github.com/brendel-group/objects-compositional-generalization/blob/HEAD/src/datasets/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":"7d33f028f090984d"}},{"code_sha256_prefix":"b2afa78cdfd900a4","entry":"compute_relative_performance","repo":"brendel-group/objects-compositional-generalization","repo_kind":"official","path":"src/identifiability_evaluation/evaluation.py","file_url":"https://github.com/brendel-group/objects-compositional-generalization/blob/HEAD/src/identifiability_evaluation/evaluation.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":"b2afa78cdfd900a4"}},{"code_sha256_prefix":"70d1c9fdb7ec7bdd","entry":"hungarian_algorithm","repo":"brendel-group/objects-compositional-generalization","repo_kind":"official","path":"src/identifiability_evaluation/matching.py","file_url":"https://github.com/brendel-group/objects-compositional-generalization/blob/HEAD/src/identifiability_evaluation/matching.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":"70d1c9fdb7ec7bdd"}},{"code_sha256_prefix":"d41764f3d957a830","entry":"hungarian_slots_loss","repo":"brendel-group/objects-compositional-generalization","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/brendel-group/objects-compositional-generalization/blob/HEAD/src/metrics.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":"d41764f3d957a830"}},{"code_sha256_prefix":"aec878a7da0179b8","entry":"r2_score","repo":"brendel-group/objects-compositional-generalization","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/brendel-group/objects-compositional-generalization/blob/HEAD/src/metrics.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":"aec878a7da0179b8"}},{"code_sha256_prefix":"104057979a24878a","entry":"stochastic_hungarian_algorithm","repo":"brendel-group/objects-compositional-generalization","repo_kind":"official","path":"src/identifiability_evaluation/matching.py","file_url":"https://github.com/brendel-group/objects-compositional-generalization/blob/HEAD/src/identifiability_evaluation/matching.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":"104057979a24878a"}},{"code_sha256_prefix":"84d74bb02b56abeb","entry":"categorical_loss","repo":"brendel-group/objects-compositional-generalization","repo_kind":"official","path":"src/identifiability_evaluation/matching.py","file_url":"https://github.com/brendel-group/objects-compositional-generalization/blob/HEAD/src/identifiability_evaluation/matching.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":"84d74bb02b56abeb"}},{"code_sha256_prefix":"9b0db5db94c4144b","entry":"image_r2_score","repo":"brendel-group/objects-compositional-generalization","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/brendel-group/objects-compositional-generalization/blob/HEAD/src/metrics.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":"9b0db5db94c4144b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}