SiRA: Sparse Mixture of Low Rank Adaptation

Yixin Zhu,Nevan Wichers, Cheng-Tao Lin,Xinyi Wang,Tianlong Chen,Lei Shu,Lu Han, Canglan Liu,Liangchen Luo,Jindong Chen, Meng Li

arXiv (Cornell University)(2023)

引用 0|浏览9
暂无评分
摘要
Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks. Most previous works considers adding the dense trainable parameters, where all parameters are used to adapt certain task. We found this less effective empirically using the example of LoRA that introducing more trainable parameters does not help. Motivated by this we investigate the importance of leveraging "sparse" computation and propose SiRA: sparse mixture of low rank adaption. SiRA leverages the Sparse Mixture of Expert(SMoE) to boost the performance of LoRA. Specifically it enforces the top $k$ experts routing with a capacity limit restricting the maximum number of tokens each expert can process. We propose a novel and simple expert dropout on top of gating network to reduce the over-fitting issue. Through extensive experiments, we verify SiRA performs better than LoRA and other mixture of expert approaches across different single tasks and multitask settings.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要