{"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/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"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.12550"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.12550"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.12550\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2402.12550"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.12550\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.12550"},"call":"get_concepts_for_paper(arxiv_id=\"2402.12550\")"}],"by_repo":[{"repo":"james-oldfield/mmoe","kind":"official","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"james-oldfield/mumoe","kind":"official","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"karpathy/nanoGPT","kind":"found_in_text","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lucidrains/mlp-mixer-pytorch","kind":"found_in_text","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2105.01601"],"harvested_for_calls":[{"arxiv_id":"2105.01601","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.01601"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.01601\")"}]}],"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","assemblies":[{"assembly_sha256":"84c804b488be1598","source_kind":"harvested","method_name":"Multilinear Mixture of Experts (µMoE)","realizes_method":"Multilinear Mixture of Experts (µMoE)","graph_method":"Multilinear Mixture of Experts (µMoE)","realizes_severed":false,"claim":"The code implements a factorized Mixture of Experts model using CANDECOMP/PARAFAC (CP) decomposition to enable scalable expert specialization.","centrality":"contribution","entry":"CPMuMoE","entry_sha256":"2c5c07798b6a1ce0","n_bricks":1,"bricks":[{"entry":"CPMuMoE","code_sha256":"2c5c07798b6a1ce0","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"765c12a0b57c","n_siblings":0,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"765c12a0b57c","realizes_method":"Multilinear Mixture of Experts (µMoE)","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["84c804b488be1598"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"2402.12550"},"call":"assembly(arxiv_id=\"2402.12550\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2402.12550.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2402.12550.svg"},"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":3,"ran_honours":1},"n_samples":4,"n_ran":4,"n_constructed":1,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":4,"ran":4,"n_ran_checked":4,"n_instrument":0,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":4,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"2c5c07798b6a1ce0","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,"fixture_out_type":"CPMuMoE","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, james-oldfield/mumoe when it was checked","mcp_get_code":{"code_sha256":"2c5c07798b6a1ce0"}},{"code_sha256":"2fc4dad707b9fa54","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,"signature":"start_value:float/0/float, end_value:float/0/float, num_steps:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/cosine-decay","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, james-oldfield/mmoe when it was checked","mcp_get_code":{"code_sha256":"2fc4dad707b9fa54"}},{"code_sha256":"5b1aa5e31b02bda4","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,"signature":"start_value:float/0/float, end_value:float/0/float, num_steps:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/linear-decay","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, james-oldfield/mmoe when it was checked","mcp_get_code":{"code_sha256":"5b1aa5e31b02bda4"}},{"code_sha256":"32f08e6e8ce8238e","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_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"number:float/0/float, decimals:int/0/int","fixture_out_type":"float","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"32f08e6e8ce8238e"},"code_page":"/code/truncate","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, james-oldfield/mmoe when it was checked","mcp_get_code":{"code_sha256":"32f08e6e8ce8238e"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"18e3caa411cf52881134e4834ea63b2c51d354b7e400b0df5e5e8d834e8152ec","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}