{"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-symmetry-ensembles-improving-diversity","title":"Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries","arxiv_id":"2303.02484","date":"2023-03-04","proceeding":null,"authors":["Charlotte Loh","Seungwook Han","Shivchander Sudalairaj","Rumen Dangovski","Kai Xu","Florian Wenzel","Marin Soljacic","Akash Srivastava"],"abstract":"Deep ensembles (DE) have been successful in improving model performance by learning diverse members via the stochasticity of random initialization. While recent works have attempted to promote further diversity in DE via hyperparameters or regularizing loss functions, these methods primarily still rely on a stochastic approach to explore the hypothesis space. In this work, we present Multi-Symmetry Ensembles (MSE), a framework for constructing diverse ensembles by capturing the multiplicity of hypotheses along symmetry axes, which explore the hypothesis space beyond stochastic perturbations of model weights and hyperparameters. We leverage recent advances in contrastive representation learning to create models that separately capture opposing hypotheses of invariant and equivariant functional classes and present a simple ensembling approach to efficiently combine appropriate hypotheses for a given task. We show that MSE effectively captures the multiplicity of conflicting hypotheses that is often required in large, diverse datasets like ImageNet. As a result of their inherent diversity, MSE improves classification performance, uncertainty quantification, and generalization across a series of transfer tasks.","url_abs":"https://arxiv.org/abs/2303.02484v2","url_pdf":"https://arxiv.org/pdf/2303.02484v2.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-symmetry-ensembles-improving-diversity","repo_url":"https://github.com/clott3/multi-sym-ensem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.02484","atlas_url":"https://app.syntology.ai/?focus=2303.02484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02484"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clott3/multi-sym-ensem","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"0a1deb0dd27fb2f7","entry":"EnsembleSSL","repo":"clott3/multi-sym-ensem","repo_kind":"official","path":"networks.py","file_url":"https://github.com/clott3/multi-sym-ensem/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a1deb0dd27fb2f7"}},{"code_sha256_prefix":"c13c39acc4dc571c","entry":"MLP","repo":"clott3/multi-sym-ensem","repo_kind":"official","path":"networks.py","file_url":"https://github.com/clott3/multi-sym-ensem/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c13c39acc4dc571c"}},{"code_sha256_prefix":"878c466cd0fa324b","entry":"consume_prefix_in_state_dict_if_present","repo":"clott3/multi-sym-ensem","repo_kind":"official","path":"networks.py","file_url":"https://github.com/clott3/multi-sym-ensem/blob/HEAD/networks.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":"878c466cd0fa324b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}