稀疏调优增强基于预训练模型的持续学习中的可塑性
Sparse Tuning Enhances Plasticity in PTM-based Continual Learning
AI总结：
针对基于预训练模型的持续学习中冻结法可塑性不足、全量微调易破坏预训练知识的问题，提出即插即用的互信息引导稀疏调优方法MIST，可在极小参数更新规模下提升多基线的持续学习性能。
摘要：
基于预训练模型（PTM）的持续学习在跨序列任务高效适配方面具备极大潜力。但现有多数方法会冻结PTM，依赖提示词或适配器等辅助模块，限制了模型可塑性，在面临显著分布偏移时会导致泛化性能次优。虽然全量微调可提升适配能力，但存在破坏关键预训练知识的风险。本文提出互信息引导稀疏调优（MIST）这一即插即用方法，其基于参数对互信息目标的敏感度，选择性更新占比不足5%的小部分PTM参数，可在保留泛化能力的同时实现高效的特定任务适配。为进一步降低干扰，我们在调优过程中通过随机丢弃梯度引入强稀疏正则化，使得每步更新的参数占比不足0.5%。将MIST应用于标准基于冻结的方法之前，可在各类持续学习基准上稳定提升性能。实验表明，将本方法集成到多个基线中可带来显著性能提升，代码可在https://github.com/zhwhu/MIST获取。
英文摘要：
Continual Learning with Pre-trained Models holds great promise for efficient adaptation across sequential tasks. However, most existing approaches freeze PTMs and rely on auxiliary modules like prompts or adapters, limiting model plasticity and leading to suboptimal generalization when facing significant distribution shifts. While full fine-tuning can improve adaptability, it risks disrupting crucial pre-trained knowledge. In this paper, we propose Mutual Information-guided Sparse Tuning (MIST), a plug-and-play method that selectively updates a small subset of PTM parameters, less than 5%, based on sensitivity to mutual information objectives. MIST enables effective task-specific adaptation while preserving generalization. To further reduce interference, we introduce strong sparsity regularization by randomly dropping gradients during tuning, resulting in fewer than 0.5% of parameters being updated per step. Applied before standard freeze-based methods, MIST consistently boosts performance across diverse continual learning benchmarks. Experiments show that integrating our method into multiple baselines yields significant performance gains. Our code is available at https://github.com/zhwhu/MIST.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
