TreeLoRA：通过层级梯度相似性树引导的逐层LoRA实现高效持续学习
TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree
AI总结：
提出TreeLoRA方法，利用层级梯度相似性构建逐层适配器，结合bandit技术高效探索任务结构，并通过稀疏梯度更新优化参数，实现大预训练模型的高效持续学习。
摘要：
许多现实世界应用在流式环境中收集数据，其中学习任务按顺序出现。这需要持续学习（CL）在线更新模型，以适应新任务同时保留过去知识以防止灾难性遗忘。如今，随着大型预训练模型（LPM）的蓬勃发展，由于其巨大的计算需求和不断增长的参数规模，效率对于CL变得日益关键。在本文中，我们引入TreeLoRA（低秩适配器的K-D树），一种通过利用层级梯度相似性构建逐层适配器以实现高效CL（特别是针对LPM）的新方法。为了减少任务相似性估计的计算负担，我们采用bandit技术开发了一种基于较低置信度界限的算法，以高效探索任务结构。此外，我们使用稀疏梯度更新促进参数优化，使该方法更适合LPM。提供了理论分析以证明我们方法背后的合理性，并且在视觉变换器（ViT）和大语言模型（LLM）上的实验展示了我们方法在包括视觉和自然语言处理任务在内的各个领域的有效性和效率。
英文摘要：
Many real-world applications collect data in a streaming environment, where learning tasks are encountered sequentially. This necessitates continual learning (CL) to update models online, enabling adaptation to new tasks while preserving past knowledge to prevent catastrophic forgetting. Nowadays, with the flourish of large pre-trained models (LPMs), efficiency has become increasingly critical for CL, due to their substantial computational demands and growing parameter sizes. In this paper, we introduce TreeLoRA (K-D Tree of Low-Rank Adapters), a novel approach that constructs layer-wise adapters by leveraging hierarchical gradient similarity to enable efficient CL, particularly for LPMs. To reduce the computational burden of task similarity estimation, we employ bandit techniques to develop an algorithm based on lower confidence bounds to efficiently explore the task structure. Furthermore, we use sparse gradient updates to facilitate parameter optimization, making the approach better suited for LPMs. Theoretical analysis is provided to justify the rationale behind our approach, and experiments on both vision transformers (ViTs) and large language models (LLMs) demonstrate the effectiveness and efficiency of our approach across various domains, including vision and natural language processing tasks.
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。
