{"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/direct-feedback-alignment-scales-to-modern","title":"Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures","arxiv_id":"2006.12878","date":"2020-06-23","proceeding":"NeurIPS 2020 12","authors":["Julien Launay","Iacopo Poli","François Boniface","Florent Krzakala"],"abstract":"Despite being the workhorse of deep learning, the backpropagation algorithm is no panacea. It enforces sequential layer updates, thus preventing efficient parallelization of the training process. Furthermore, its biological plausibility is being challenged. Alternative schemes have been devised; yet, under the constraint of synaptic asymmetry, none have scaled to modern deep learning tasks and architectures. Here, we challenge this perspective, and study the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural language processing. In contrast with previous studies limited to computer vision tasks, our findings show that it successfully trains a large range of state-of-the-art deep learning architectures, with performance close to fine-tuned backpropagation. At variance with common beliefs, our work supports that challenging tasks can be tackled in the absence of weight transport.","url_abs":"https://arxiv.org/abs/2006.12878v2","url_pdf":"https://arxiv.org/pdf/2006.12878v2.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":"direct-feedback-alignment-scales-to-modern","repo_url":"https://github.com/lightonai/dfa-scales-to-modern-deep-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.12878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12878"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/lightonai/dfa-scales-to-modern-deep-learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"4b36f632eb1ccc80","entry":"get_data","repo":"lightonai/dfa-scales-to-modern-deep-learning","repo_kind":"official","path":"paper-experiments/geometric-learning/alignment.py","file_url":"https://github.com/lightonai/dfa-scales-to-modern-deep-learning/blob/HEAD/paper-experiments/geometric-learning/alignment.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":"4b36f632eb1ccc80"}},{"code_sha256_prefix":"57e0043966887f1b","entry":"get_data","repo":"lightonai/dfa-scales-to-modern-deep-learning","repo_kind":"official","path":"paper-experiments/geometric-learning/autoencoder.py","file_url":"https://github.com/lightonai/dfa-scales-to-modern-deep-learning/blob/HEAD/paper-experiments/geometric-learning/autoencoder.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":"57e0043966887f1b"}},{"code_sha256_prefix":"b3c53775e578f268","entry":"get_data","repo":"lightonai/dfa-scales-to-modern-deep-learning","repo_kind":"official","path":"paper-experiments/geometric-learning/geometric.py","file_url":"https://github.com/lightonai/dfa-scales-to-modern-deep-learning/blob/HEAD/paper-experiments/geometric-learning/geometric.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":"b3c53775e578f268"}},{"code_sha256_prefix":"9a9bbcf0acab0876","entry":"get_data","repo":"lightonai/dfa-scales-to-modern-deep-learning","repo_kind":"official","path":"paper-experiments/geometric-learning/tsne.py","file_url":"https://github.com/lightonai/dfa-scales-to-modern-deep-learning/blob/HEAD/paper-experiments/geometric-learning/tsne.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":"9a9bbcf0acab0876"}},{"code_sha256_prefix":"45e3ddd9c9803f5e","entry":"get_device","repo":"lightonai/dfa-scales-to-modern-deep-learning","repo_kind":"official","path":"paper-experiments/geometric-learning/alignment.py","file_url":"https://github.com/lightonai/dfa-scales-to-modern-deep-learning/blob/HEAD/paper-experiments/geometric-learning/alignment.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":"45e3ddd9c9803f5e"}},{"code_sha256_prefix":"6bb2b9249518fd2f","entry":"keep_indices","repo":"lightonai/dfa-scales-to-modern-deep-learning","repo_kind":"official","path":"TinyDFA/tinydfa/utils.py","file_url":"https://github.com/lightonai/dfa-scales-to-modern-deep-learning/blob/HEAD/TinyDFA/tinydfa/utils.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":"6bb2b9249518fd2f"}},{"code_sha256_prefix":"4beba5bae36d22cd","entry":"remove_indices","repo":"lightonai/dfa-scales-to-modern-deep-learning","repo_kind":"official","path":"TinyDFA/tinydfa/utils.py","file_url":"https://github.com/lightonai/dfa-scales-to-modern-deep-learning/blob/HEAD/TinyDFA/tinydfa/utils.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":"4beba5bae36d22cd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}