{"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/on-the-representation-collapse-of-sparse","title":"On the Representation Collapse of Sparse Mixture of Experts","arxiv_id":"2204.09179","date":"2022-04-20","proceeding":null,"authors":["Zewen Chi","Li Dong","Shaohan Huang","Damai Dai","Shuming Ma","Barun Patra","Saksham Singhal","Payal Bajaj","Xia Song","Xian-Ling Mao","Heyan Huang","Furu Wei"],"abstract":"Sparse mixture of experts provides larger model capacity while requiring a constant computational overhead. It employs the routing mechanism to distribute input tokens to the best-matched experts according to their hidden representations. However, learning such a routing mechanism encourages token clustering around expert centroids, implying a trend toward representation collapse. In this work, we propose to estimate the routing scores between tokens and experts on a low-dimensional hypersphere. We conduct extensive experiments on cross-lingual language model pre-training and fine-tuning on downstream tasks. Experimental results across seven multilingual benchmarks show that our method achieves consistent gains. We also present a comprehensive analysis on the representation and routing behaviors of our models. Our method alleviates the representation collapse issue and achieves more consistent routing than the baseline mixture-of-experts methods.","url_abs":"https://arxiv.org/abs/2204.09179v3","url_pdf":"https://arxiv.org/pdf/2204.09179v3.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":"on-the-representation-collapse-of-sparse","repo_url":"https://github.com/microsoft/unilm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-the-representation-collapse-of-sparse","repo_url":"https://github.com/microsoft/torchscale","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"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":null,"atlas_url":"https://app.syntology.ai/?focus=2204.09179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.09179"}},"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/microsoft/torchscale","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/unilm","reach":null}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"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":"4b3cc005618b1ec8","entry":"entropy","repo":"microsoft/torchscale","repo_kind":"listed","path":"torchscale/component/xmoe/routing.py","file_url":"https://github.com/microsoft/torchscale/blob/HEAD/torchscale/component/xmoe/routing.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b3cc005618b1ec8"}},{"code_sha256_prefix":"9d133667851a7737","entry":"one_hot","repo":"microsoft/torchscale","repo_kind":"listed","path":"torchscale/component/xmoe/routing.py","file_url":"https://github.com/microsoft/torchscale/blob/HEAD/torchscale/component/xmoe/routing.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d133667851a7737"}},{"code_sha256_prefix":"3fda9eba93c58bf6","entry":"top1gating","repo":"microsoft/torchscale","repo_kind":"listed","path":"torchscale/component/xmoe/routing.py","file_url":"https://github.com/microsoft/torchscale/blob/HEAD/torchscale/component/xmoe/routing.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":"3fda9eba93c58bf6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}