{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/reverse-engineering-self-supervised-learning-1","title":"Reverse Engineering Self-Supervised Learning","arxiv_id":"2305.15614","date":"2023-05-24","proceeding":"NeurIPS 2023 11","authors":["Ido Ben-Shaul","Ravid Shwartz-Ziv","Tomer Galanti","Shai Dekel","Yann Lecun"],"abstract":"Self-supervised learning (SSL) is a powerful tool in machine learning, but understanding the learned representations and their underlying mechanisms remains a challenge. This paper presents an in-depth empirical analysis of SSL-trained representations, encompassing diverse models, architectures, and hyperparameters. Our study reveals an intriguing aspect of the SSL training process: it inherently facilitates the clustering of samples with respect to semantic labels, which is surprisingly driven by the SSL objective's regularization term. This clustering process not only enhances downstream classification but also compresses the data information. Furthermore, we establish that SSL-trained representations align more closely with semantic classes rather than random classes. Remarkably, we show that learned representations align with semantic classes across various hierarchical levels, and this alignment increases during training and when moving deeper into the network. Our findings provide valuable insights into SSL's representation learning mechanisms and their impact on performance across different sets of classes.","url_abs":"https://arxiv.org/abs/2305.15614v2","url_pdf":"https://arxiv.org/pdf/2305.15614v2.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":"reverse-engineering-self-supervised-learning-1","repo_url":"https://github.com/lightly-ai/lightly","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.15614","atlas_url":"https://app.syntology.ai/?focus=2305.15614","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2305.15614"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2305.15614\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2305.15614"},"call":"get_concepts_for_paper(arxiv_id=\"2305.15614\")"}],"by_repo":[{"repo":"lightly-ai/lightly","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":11,"harvested_for":["1911.05722","2002.05709","2006.09882","2011.10566","2103.03230","2104.14548","2105.04906","2204.07141","2207.06167","2210.01571","2301.08243"],"harvested_for_calls":[{"arxiv_id":"1911.05722","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1911.05722"},"call":"get_harvested_code_for_paper(arxiv_id=\"1911.05722\")"},{"arxiv_id":"2002.05709","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.05709"},"call":"get_harvested_code_for_paper(arxiv_id=\"2002.05709\")"},{"arxiv_id":"2006.09882","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.09882"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.09882\")"},{"arxiv_id":"2011.10566","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2011.10566"},"call":"get_harvested_code_for_paper(arxiv_id=\"2011.10566\")"},{"arxiv_id":"2103.03230","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.03230"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.03230\")"},{"arxiv_id":"2104.14548","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.14548"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.14548\")"},{"arxiv_id":"2105.04906","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.04906"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.04906\")"},{"arxiv_id":"2204.07141","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.07141"},"call":"get_harvested_code_for_paper(arxiv_id=\"2204.07141\")"},{"arxiv_id":"2207.06167","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.06167"},"call":"get_harvested_code_for_paper(arxiv_id=\"2207.06167\")"},{"arxiv_id":"2210.01571","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.01571"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.01571\")"},{"arxiv_id":"2301.08243","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.08243"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.08243\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bc0370c30afadfc9368ab5e865c9ccce064c7d2eb5870980731d1c7b6be761cf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}