{"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/enhancing-efficiency-in-sparse-models-with","title":"XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection","arxiv_id":"2403.18926","date":"2024-02-27","proceeding":null,"authors":["Yuanhang Yang","shiyi qi","Wenchao Gu","Chaozheng Wang","Cuiyun Gao","Zenglin Xu"],"abstract":"Sparse models, including sparse Mixture-of-Experts (MoE) models, have emerged as an effective approach for scaling Transformer models. However, they often suffer from computational inefficiency since a significant number of parameters are unnecessarily involved in computations via multiplying values by zero or low activation values. To address this issue, we present \\tool, a novel MoE designed to enhance both the efficacy and efficiency of sparse MoE models. \\tool leverages small experts and a threshold-based router to enable tokens to selectively engage only essential parameters. Our extensive experiments on language modeling and machine translation tasks demonstrate that \\tool can enhance model performance while decreasing the computation load at MoE layers by over 50\\% without sacrificing performance. Furthermore, we present the versatility of \\tool by applying it to dense models, enabling sparse computation during inference. We provide a comprehensive analysis and make our code available at https://github.com/ysngki/XMoE.","url_abs":"https://arxiv.org/abs/2403.18926v2","url_pdf":"https://arxiv.org/pdf/2403.18926v2.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":"enhancing-efficiency-in-sparse-models-with","repo_url":"https://github.com/ysngki/xmoe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.18926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18926"}},"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/ysngki/xmoe","reach":{"status":"ok"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"1f4447581128a711","entry":"get_batch","repo":"ysngki/xmoe","repo_kind":"official","path":"MoE-Megatron-DeepSpeed/pretrain_vision_classify.py","file_url":"https://github.com/ysngki/xmoe/blob/HEAD/MoE-Megatron-DeepSpeed/pretrain_vision_classify.py","link_basis":"harvester_set","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":"1f4447581128a711"}},{"code_sha256_prefix":"92287bdc91b8ac90","entry":"get_batch","repo":"ysngki/xmoe","repo_kind":"official","path":"MoE-Megatron-DeepSpeed/pretrain_vision_dino.py","file_url":"https://github.com/ysngki/xmoe/blob/HEAD/MoE-Megatron-DeepSpeed/pretrain_vision_dino.py","link_basis":"harvester_set","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":"92287bdc91b8ac90"}},{"code_sha256_prefix":"edf213e729a014e0","entry":"get_batch","repo":"ysngki/xmoe","repo_kind":"official","path":"MoE-Megatron-DeepSpeed/pretrain_vision_inpaint.py","file_url":"https://github.com/ysngki/xmoe/blob/HEAD/MoE-Megatron-DeepSpeed/pretrain_vision_inpaint.py","link_basis":"harvester_set","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":"edf213e729a014e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}