{"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/learninghome-crowdsourced-training-of-large","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","arxiv_id":"2002.04013","date":"2020-02-10","proceeding":"NeurIPS 2020 12","authors":["Max Ryabinin","Anton Gusev"],"abstract":"Many recent breakthroughs in deep learning were achieved by training increasingly larger models on massive datasets. However, training such models can be prohibitively expensive. For instance, the cluster used to train GPT-3 costs over \\$250 million. As a result, most researchers cannot afford to train state of the art models and contribute to their development. Hypothetically, a researcher could crowdsource the training of large neural networks with thousands of regular PCs provided by volunteers. The raw computing power of a hundred thousand \\$2500 desktops dwarfs that of a \\$250M server pod, but one cannot utilize that power efficiently with conventional distributed training methods. In this work, we propose Learning@home: a novel neural network training paradigm designed to handle large amounts of poorly connected participants. We analyze the performance, reliability, and architectural constraints of this paradigm and compare it against existing distributed training techniques.","url_abs":"https://arxiv.org/abs/2002.04013v3","url_pdf":"https://arxiv.org/pdf/2002.04013v3.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":"learninghome-crowdsourced-training-of-large","repo_url":"https://github.com/mryab/learning-at-home","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learninghome-crowdsourced-training-of-large","repo_url":"https://github.com/learning-at-home/hivemind","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.04013","atlas_url":"https://app.syntology.ai/?focus=2002.04013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.04013"}},"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/mryab/learning-at-home","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/learning-at-home/hivemind","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"3b1727e0cc33f641","entry":"get_non_expert_params","repo":"mryab/learning-at-home","repo_kind":"official","path":"experiments/convergence/dmoe_emulator.py","file_url":"https://github.com/mryab/learning-at-home/blob/HEAD/experiments/convergence/dmoe_emulator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3b1727e0cc33f641"}},{"code_sha256_prefix":"51c376315522795b","entry":"measure_perf","repo":"mryab/learning-at-home","repo_kind":"official","path":"experiments/throughput/baseline_throughput.py","file_url":"https://github.com/mryab/learning-at-home/blob/HEAD/experiments/throughput/baseline_throughput.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"51c376315522795b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}