@inproceedings{feng-etal-2025-comoe,
    title = "{C}o{M}o{E}: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning",
    author = "Feng, Jinyuan  and
      Wei, ChaoPeng  and
      Qiu, Tenghai  and
      Hu, Tianyi  and
      Pu, Zhiqiang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.398/",
    doi = "10.18653/v1/2025.findings-emnlp.398",
    pages = "7533--7551",
    ISBN = "979-8-89176-335-7",
    abstract = "In parameter-efficient fine-tuning, mixture-of-experts (MoE), which involves specializing functionalities into different experts and sparsely activating them appropriately, has been widely adopted as a promising approach to trade-off between model capacity and computation overhead. However, current MoE variants fall short on heterogeneous datasets, ignoring the fact that experts may learn similar knowledge, resulting in the underutilization of MoE{'}s capacity. In this paper, we propose Contrastive Representation for MoE (CoMoE), a novel method to promote modularization and specialization in MoE, where the experts are trained along with a contrastive objective by sampling from activated and inactivated experts in top-k routing. We demonstrate that such a contrastive objective recovers the mutual-information gap between inputs and the two types of experts. Experiments on several benchmarks and in multi-task settings demonstrate that CoMoE can consistently enhance MoE{'}s capacity and promote modularization among the experts."
}