通过渐进式适配模块，用更少参数实现多任务高效学习。
Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
- 前层共享适配模块，后层逐步变任务专属，减少干扰。
- 在PASCAL和NYUD-v2上性能超越已有方法，参数更少。
- 适合资源受限场景下的多任务模型微调，如边缘设备。
参数高效微调方法为将预训练模型适配到下游任务提供了有前景的解决方案。尽管这些方法在单任务学习中表现良好，但在多任务学习中因可训练参数有限，会加剧任务干扰和负迁移问题。为此，我们提出一种渐进式任务特异性多任务适应方法。该方法引入适配模块：早期层共享，后期层逐渐变为任务专属；同时提出基于梯度的任务相似性计算方法，据此将相似任务分配至共享适配模块。我们在PASCAL和NYUD-v2数据集上对Swin和Pyramid Vision Transformers进行评估，结果表明，该方法在使用更少可训练参数的情况下，优于现有参数高效多任务方法。
原文摘要 · Abstract (English)
Parameter-efficient fine-tuning methods have emerged as a promising solution for adapting pre-trained models to various downstream tasks. While these methods perform well in single-task learning, extending them to multi-task learning exacerbates common issues, such as task interference and negative transfer, due to the limited number of trainable parameters. To address these challenges, we introduce progressive task-specific multi-task adaptation, a novel parameter-efficient approach for multi-task learning. Our approach introduces adapter modules that are shared in early layers and become increasingly task-specific in later layers. Additionally, we propose a gradient-based approach for computing task similarity and use this measure to allocate similar tasks to the shared adapter modules. To evaluate our approach, we adapt Swin and Pyramid Vision Transformers on PASCAL and NYUD-v2. On both datasets, our approach outperforms prior parameter-efficient multi-task methods while using fewer trainable parameters.
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。