{"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-role-of-entropy-and-reconstruction-in","title":"The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning","arxiv_id":"2307.10907","date":"2023-07-20","proceeding":null,"authors":["Borja Rodríguez-Gálvez","Arno Blaas","Pau Rodríguez","Adam Goliński","Xavier Suau","Jason Ramapuram","Dan Busbridge","Luca Zappella"],"abstract":"The mechanisms behind the success of multi-view self-supervised learning (MVSSL) are not yet fully understood. Contrastive MVSSL methods have been studied through the lens of InfoNCE, a lower bound of the Mutual Information (MI). However, the relation between other MVSSL methods and MI remains unclear. We consider a different lower bound on the MI consisting of an entropy and a reconstruction term (ER), and analyze the main MVSSL families through its lens. Through this ER bound, we show that clustering-based methods such as DeepCluster and SwAV maximize the MI. We also re-interpret the mechanisms of distillation-based approaches such as BYOL and DINO, showing that they explicitly maximize the reconstruction term and implicitly encourage a stable entropy, and we confirm this empirically. We show that replacing the objectives of common MVSSL methods with this ER bound achieves competitive performance, while making them stable when training with smaller batch sizes or smaller exponential moving average (EMA) coefficients. Github repo: https://github.com/apple/ml-entropy-reconstruction.","url_abs":"https://arxiv.org/abs/2307.10907v2","url_pdf":"https://arxiv.org/pdf/2307.10907v2.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-role-of-entropy-and-reconstruction-in","repo_url":"https://github.com/apple/ml-entropy-reconstruction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"byol","method_name":"BYOL"},{"method_slug":"deepcluster","method_name":"DeepCluster"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"lars","method_name":"LARS"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"swav","method_name":"SwAV"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"},{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.10907","atlas_url":"https://app.syntology.ai/?focus=2307.10907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10907"}},"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/apple/ml-entropy-reconstruction","reach":null}],"summary":{"ran_fixture":2},"by_repo_kind":{"official":{"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":"5d7c8a7590c98650","entry":"entropy","repo":"apple/ml-entropy-reconstruction","repo_kind":"official","path":"entropy_reconstruction.py","file_url":"https://github.com/apple/ml-entropy-reconstruction/blob/HEAD/entropy_reconstruction.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5d7c8a7590c98650"}},{"code_sha256_prefix":"c19e7e55846f87d4","entry":"reconstruction","repo":"apple/ml-entropy-reconstruction","repo_kind":"official","path":"entropy_reconstruction.py","file_url":"https://github.com/apple/ml-entropy-reconstruction/blob/HEAD/entropy_reconstruction.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c19e7e55846f87d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}