动态调整模型合并时机，缓解大模型持续学习中的遗忘问题。
AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning
- 根据训练轨迹自动判断合并时机与频率。
- 在多个基准上实现平均80%的FWT提升。
- 适合需要长期更新的大模型部署场景。
持续学习（CL）对于在动态现实环境中部署大语言模型（LLMs）至关重要，避免昂贵的重新训练。基于模型合并的方法虽受关注，但仍难以有效平衡新知识学习与遗忘控制，主要因合并次数和频率欠优。本文提出自适应迭代模型合并（AimMerging），利用训练轨迹中的学习与遗忘信号动态监控模型状态。训练轨迹引导的合并控制器自适应决定迭代融合的时机与频率，基于回放的知识融合模块计算合并权重并执行融合。在三个不同规模（770M至13B）的CL基准上的全面实验表明，AimMerging相比现有最先进方法，在FWT和BWT上分别取得平均80%和59%的相对提升。源代码已公开以保证可复现性。
原文摘要 · Abstract (English)
Continual learning (CL) is essential for deploying large language models (LLMs) in dynamic real-world environments without the need for costly retraining. Recent model merging-based methods have attracted significant attention, but they still struggle to effectively manage the trade-off between learning new knowledge and preventing forgetting, a challenge largely stemming from suboptimal number of merges and merging frequency. In this paper, we introduce Adaptive Iterative Model Merging (AimMerging), a novel CL framework that utilizes learning and forgetting signals from the training trajectory to dynamically monitor the model's training status. Guided by dynamic monitoring, the training trajectory-guided merge controller adaptively determines the timing and frequency of iterative fusion, while the rehearsal-based knowledge fusion module computes the merging weights and executes the fusion. Comprehensive experiments on three CL benchmarks with various model sizes (from 770M to 13B) demonstrate that AimMerging achieves significant performance improvements over existing state-of-the-art methods, with an average relative improvement of 80% and 59% on FWT and BWT, respectively. The source code is provided for reproducibility.
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。