分离共享与领域特定LoRA，提升多领域学习效果
Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning
- 让共享与专属LoRA分别位于预训练权重的不同子空间
- 在三个动作识别数据集上验证有效，部分场景性能更优
- 适合研究多领域适配器设计的开发者参考
现有多领域学习架构采用两类适配器：适用于所有领域的共享LoRA和针对每个特定领域的领域专属LoRA。然而，这种结构是否有效捕捉领域特异性信息仍不明确。本文提出一种方法，确保共享与领域特定的LoRA存在于不同的子空间中，即预训练权重的列空间与左零空间。我们将该方法应用于三个数据集（UCF101、Kinetics400 和 HMDB51）的动作识别任务，展示了其在某些情况下的有效性，并分析了LoRA权重维度的影响。
原文摘要 · Abstract (English)
Existing architectures of multi-domain learning have two types of adapters: shared LoRA for all domains and domain-specific LoRA for each particular domain. However, it remains unclear whether this structure effectively captures domain-specific information. In this paper, we propose a method that ensures that shared and domain-specific LoRAs exist in different subspaces; specifically, the column and left null subspaces of the pre-trained weights. We apply the proposed method to action recognition with three datasets (UCF101, Kinetics400, and HMDB51) and demonstrate its effectiveness in some cases along with the analysis of the dimensions of LoRA weights.
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。