{"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/the-scattering-compositional-learner","title":"The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning","arxiv_id":"2007.04212","date":"2020-07-08","proceeding":null,"authors":["Yuhuai Wu","Honghua Dong","Roger Grosse","Jimmy Ba"],"abstract":"In this work, we focus on an analogical reasoning task that contains rich compositional structures, Raven's Progressive Matrices (RPM). To discover compositional structures of the data, we propose the Scattering Compositional Learner (SCL), an architecture that composes neural networks in a sequence. Our SCL achieves state-of-the-art performance on two RPM datasets, with a 48.7% relative improvement on Balanced-RAVEN and 26.4% on PGM over the previous state-of-the-art. We additionally show that our model discovers compositional representations of objects' attributes (e.g., shape color, size), and their relationships (e.g., progression, union). We also find that the compositional representation makes the SCL significantly more robust to test-time domain shifts and greatly improves zero-shot generalization to previously unseen analogies.","url_abs":"https://arxiv.org/abs/2007.04212v1","url_pdf":"https://arxiv.org/pdf/2007.04212v1.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":"the-scattering-compositional-learner","repo_url":"https://github.com/dhh1995/SCL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-scattering-compositional-learner","repo_url":"https://github.com/lucidrains/scattering-compositional-learner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-scattering-compositional-learner","repo_url":"https://github.com/mikomel/scattering-compositional-learner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"pgm","method_name":"PGM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.04212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.04212"}},"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/lucidrains/scattering-compositional-learner","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dhh1995/SCL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mikomel/scattering-compositional-learner","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"ran_honours":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"00bfb221f3305e25","entry":"default","repo":"lucidrains/scattering-compositional-learner","repo_kind":"listed","path":"scattering_transform/scattering_transform.py","file_url":"https://github.com/lucidrains/scattering-compositional-learner/blob/HEAD/scattering_transform/scattering_transform.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00bfb221f3305e25"}},{"code_sha256_prefix":"270b669b4662f5c1","entry":"expand_dim","repo":"lucidrains/scattering-compositional-learner","repo_kind":"listed","path":"scattering_transform/scattering_transform.py","file_url":"https://github.com/lucidrains/scattering-compositional-learner/blob/HEAD/scattering_transform/scattering_transform.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"270b669b4662f5c1"}},{"code_sha256_prefix":"003b21d8bf55bb13","entry":"extract_attrs","repo":"dhh1995/SCL","repo_kind":"official","path":"scripts/preprocess.py","file_url":"https://github.com/dhh1995/SCL/blob/HEAD/scripts/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"003b21d8bf55bb13"}},{"code_sha256_prefix":"61c7bbb3265d2bf0","entry":"parse_center","repo":"dhh1995/SCL","repo_kind":"official","path":"scripts/preprocess.py","file_url":"https://github.com/dhh1995/SCL/blob/HEAD/scripts/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61c7bbb3265d2bf0"}},{"code_sha256_prefix":"e2386c815d7ba839","entry":"parse_two_parts","repo":"dhh1995/SCL","repo_kind":"official","path":"scripts/preprocess.py","file_url":"https://github.com/dhh1995/SCL/blob/HEAD/scripts/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2386c815d7ba839"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}