面向语言模型持续学习中动态适配器组合的路由学习方法
Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models
AI总结：
针对预训练语言模型持续学习中PEFT模块训练干扰与路由组合不佳的问题，提出L2R方法，通过隔离新模块训练、基于小型记忆库训练路由器网络组合模块，在多种基准上实现更优的泛化与性能。
摘要：
参数高效微调（PEFT）方法正越来越多地与预训练语言模型（PLM）结合用于持续学习（CL）。这类方法通常为每个新任务训练一个PEFT模块，并在推理阶段采用基于相似度的选择来路由模块。但它们存在两大局限：1）模块训练时与已学习模块产生干扰；2）组合模块时路由效果欠佳。本文提出L2R方法，该方法隔离新PEFT模块的训练过程以确保其任务专用性。随后L2R通过训练一个路由器网络来学习组合已学习模块，该网络利用包含过往任务样本的小型记忆库实现。我们在两种持续学习设置下采用多个基准测试评估该方法。结果表明，L2R可实现PEFT模块的有效组合，与其他方法相比提升了泛化能力与性能。
英文摘要：
Parameter-efficient fine-tuning (PEFT) methods are increasingly used with pre-trained language models (PLMs) for continual learning (CL). These methods typically involve training a PEFT module for each new task and employing similarity-based selection to route modules during inference. However, they face two major limitations: 1) interference during module training with already learned modules and 2) suboptimal routing when composing modules. In this paper, we present L2R, a method that isolates the training of new PEFT modules to ensure their task specialization. L2R then learns to compose the learned modules by training a network of routers that leverages a small memory containing examples of previously seen tasks. We evaluate our method in two CL setups using various benchmarks. Our results demonstrate that L2R provides an effective composition of PEFT modules, leading to improved generalization and performance compared to other methods.
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。
