提出一种新方法，让多个任务模型合并后仍能保留各自特点且性能更优。
CALM: Consensus-Aware Localized Merging for Multi-Task Learning
- 基于全局任务共识优化局部参数掩码，减少冲突。
- 在多个数据集上超越现有方法，接近传统多任务学习效果。
- 适合需要高效融合多个专用模型的场景。
模型合并旨在整合多个微调模型的优势，同时保留各任务特异性能力。现有方法分为全局与局部感知两类：前者易引发参数干扰，后者难以保持任务细节的有效性。为此，本文提出共识感知的局部合并方法（CALM），通过与全局任务共识对齐的局部信息，确保合并后性能。CALM包含三个核心组件：(1) 类平衡熵最小化采样，更灵活可靠地利用无监督数据；(2) 高效感知框架，选择少量任务进行顺序合并，具备良好可扩展性；(3) 共识感知掩码优化，使局部二值掩码与全局任务共识对齐，实现无冲突合并。实验表明，CALM显著优于现有方法，表现稳健，接近传统多任务学习水平。
原文摘要 · Abstract (English)
Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task arithmetic, are typically classified into global- and local-aware methods. However, global-aware methods inevitably cause parameter interference, while local-aware methods struggle to maintain the effectiveness of task-specific details in the merged model. To address these limitations, we propose a Consensus-Aware Localized Merging (CALM) method which incorporates localized information aligned with global task consensus, ensuring its effectiveness post-merging. CALM consists of three key components: (1) class-balanced entropy minimization sampling, providing a more flexible and reliable way to leverage unsupervised data; (2) an efficient-aware framework, selecting a small set of tasks for sequential merging with high scalability; (3) a consensus-aware mask optimization, aligning localized binary masks with global task consensus and merging them conflict-free. Experiments demonstrate the superiority and robustness of our CALM, significantly outperforming existing methods and achieving performance close to traditional MTL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。