{"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/cluster-driven-expert-pruning-for-mixture-of","title":"Cluster-Driven Expert Pruning for Mixture-of-Experts Large Language Models","arxiv_id":"2504.07807","date":"2025-04-10","proceeding":null,"authors":["Hongcheng Guo","Juntao Yao","Boyang Wang","Junjia Du","Shaosheng Cao","Donglin Di","Shun Zhang","Zhoujun Li"],"abstract":"Mixture-of-Experts (MoE) architectures have emerged as a promising paradigm for scaling large language models (LLMs) with sparse activation of task-specific experts. Despite their computational efficiency during inference, the massive overall parameter footprint of MoE models (e.g., GPT-4) introduces critical challenges for practical deployment. Current pruning approaches often fail to address two inherent characteristics of MoE systems: 1).intra-layer expert homogeneity where experts within the same MoE layer exhibit functional redundancy, and 2). inter-layer similarity patterns where deeper layers tend to contain progressively more homogeneous experts. To tackle these issues, we propose Cluster-driven Expert Pruning (C-Prune), a novel two-stage framework for adaptive task-specific compression of MoE LLMs. C-Prune operates through layer-wise expert clustering, which groups functionally similar experts within each MoE layer using parameter similarity metrics, followed by global cluster pruning, which eliminates redundant clusters across all layers through a unified importance scoring mechanism that accounts for cross-layer homogeneity. We validate C-Prune through extensive experiments on multiple MoE models and benchmarks. The results demonstrate that C-Prune effectively reduces model size while outperforming existing MoE pruning methods.","url_abs":"https://arxiv.org/abs/2504.07807v1","url_pdf":"https://arxiv.org/pdf/2504.07807v1.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":"cluster-driven-expert-pruning-for-mixture-of","repo_url":"https://github.com/fighoture/moe_unsupervised_pruning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"methods":[{"method_slug":"moe","method_name":"MoE"},{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.07807","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}