{"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/multilinear-mixture-of-experts-scalable","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","arxiv_id":"2402.12550","date":"2024-02-19","proceeding":null,"authors":["James Oldfield","Markos Georgopoulos","Grigorios G. Chrysos","Christos Tzelepis","Yannis Panagakis","Mihalis A. Nicolaou","Jiankang Deng","Ioannis Patras"],"abstract":"The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the computational cost of scaling the number of experts high enough to achieve fine-grained specialization. In this paper, we propose the Multilinear Mixture of Experts ($\\mu$MoE) layer to address this, focusing on vision models. $\\mu$MoE layers enable scalable expert specialization by performing an implicit computation on prohibitively large weight tensors entirely in factorized form. Consequently, $\\mu$MoEs (1) avoid the restrictively high inference-time costs of dense MoEs, yet (2) do not inherit the training issues of the popular sparse MoEs' discrete (non-differentiable) expert routing. We present both qualitative and quantitative evidence that scaling $\\mu$MoE layers when fine-tuning foundation models for vision tasks leads to more specialized experts at the class-level, further enabling manual bias correction in CelebA attribute classification. Finally, we show qualitative results demonstrating the expert specialism achieved when pre-training large GPT2 and MLP-Mixer models with parameter-matched $\\mu$MoE blocks at every layer, maintaining comparable accuracy. Our code is available at: https://github.com/james-oldfield/muMoE.","url_abs":"https://arxiv.org/abs/2402.12550v4","url_pdf":"https://arxiv.org/pdf/2402.12550v4.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":"multilinear-mixture-of-experts-scalable","repo_url":"https://github.com/james-oldfield/mmoe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multilinear-mixture-of-experts-scalable","repo_url":"https://github.com/james-oldfield/mumoe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mlp-mixer","method_name":"MLP-Mixer"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.12550","atlas_url":"https://app.syntology.ai/?focus=2402.12550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12550"}},"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/karpathy/nanoGPT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/lucidrains/mlp-mixer-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/james-oldfield/mmoe","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/james-oldfield/mumoe","reach":null}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":2}},"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":4,"samples":[{"code_sha256_prefix":"2c5c07798b6a1ce0","entry":"CPMuMoE","repo":"james-oldfield/mumoe","repo_kind":"official","path":"MuMoE.py","file_url":"https://github.com/james-oldfield/mumoe/blob/HEAD/MuMoE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c5c07798b6a1ce0"}},{"code_sha256_prefix":"2fc4dad707b9fa54","entry":"cosine_decay","repo":"james-oldfield/mmoe","repo_kind":"official","path":"utils.py","file_url":"https://github.com/james-oldfield/mmoe/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2fc4dad707b9fa54"}},{"code_sha256_prefix":"5b1aa5e31b02bda4","entry":"linear_decay","repo":"james-oldfield/mmoe","repo_kind":"official","path":"utils.py","file_url":"https://github.com/james-oldfield/mmoe/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5b1aa5e31b02bda4"}},{"code_sha256_prefix":"32f08e6e8ce8238e","entry":"truncate","repo":"james-oldfield/mmoe","repo_kind":"official","path":"utils.py","file_url":"https://github.com/james-oldfield/mmoe/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32f08e6e8ce8238e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}