{"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/erdos-goes-neural-an-unsupervised-learning","title":"Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs","arxiv_id":"2006.10643","date":"2020-06-18","proceeding":"NeurIPS 2020 12","authors":["Nikolaos Karalias","Andreas Loukas"],"abstract":"Combinatorial optimization problems are notoriously challenging for neural networks, especially in the absence of labeled instances. This work proposes an unsupervised learning framework for CO problems on graphs that can provide integral solutions of certified quality. Inspired by Erdos' probabilistic method, we use a neural network to parametrize a probability distribution over sets. Crucially, we show that when the network is optimized w.r.t. a suitably chosen loss, the learned distribution contains, with controlled probability, a low-cost integral solution that obeys the constraints of the combinatorial problem. The probabilistic proof of existence is then derandomized to decode the desired solutions. We demonstrate the efficacy of this approach to obtain valid solutions to the maximum clique problem and to perform local graph clustering. Our method achieves competitive results on both real datasets and synthetic hard instances.","url_abs":"https://arxiv.org/abs/2006.10643v4","url_pdf":"https://arxiv.org/pdf/2006.10643v4.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":"erdos-goes-neural-an-unsupervised-learning","repo_url":"https://github.com/Stalence/erdos_neu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"erdos-goes-neural-an-unsupervised-learning","repo_url":"https://github.com/shengyu-feng/rld4co","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"combinatorial-optimization","task_name":"Combinatorial Optimization"},{"task_slug":"graph-clustering","task_name":"Graph Clustering"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.10643","atlas_url":"https://app.syntology.ai/?focus=2006.10643","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":"2006.10643"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.10643\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.10643"},"call":"get_concepts_for_paper(arxiv_id=\"2006.10643\")"}],"by_repo":[{"repo":"Stalence/erdos_neu","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.08424"],"harvested_for_calls":[{"arxiv_id":"2405.08424","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.08424"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.08424\")"}]},{"repo":"shengyu-feng/rld4co","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2502.00277"],"harvested_for_calls":[{"arxiv_id":"2502.00277","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.00277"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.00277\")"}]}],"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":"627144724d53a704b55b3a4b3ca09e4f071a61da0919a346b14beefbf537d936","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}