LoRA Dropout as a Sparsity Regularizer for Overfitting Control

Parameter-efficient fine-tuning methods, represented by LoRA, play an essential role in adapting large-scale pre-trained models to downstream tasks. However, fine-tuning LoRA-series models also faces the risk of overfitting on the training dataset, and yet there's still a lack of theoretical guidance and practical mechanism to control overfitting on LoRA-based PEFT methods. In this paper, we propose a LoRA Dropout mechanism for the LoRA-based methods by introducing random noises to the learnable low-rank matrices and increasing parameter sparsity. We then demonstrate the theoretical mechanism of our LoRA Dropout mechanism from the perspective of sparsity regularization by providing a generalization error bound under this framework. Theoretical results show that appropriate sparsity would help tighten the gap between empirical and generalization risks and thereby control overfitting. Furthermore, based on the LoRA Dropout framework, we introduce a test-time ensemble strategy and provide theoretical evidence demonstrating that the ensemble method can further compress the error bound, and lead to better performance during inference time. Extensive experiments on various NLP tasks provide practical validations of the effectiveness of our LoRA Dropout framework in improving model accuracy and calibration.

Domain Generalization through the Lens of Angular Invariance

Domain generalization (DG) aims at generalizing a classifier trained on multiple source domains to an unseen target domain with domain shift. A common pervasive theme in existing DG literature is domain-invariant representation learning with various invariance assumptions. However, prior works restrict themselves to a radical assumption for realworld challenges: If a mapping induced by a deep neural network (DNN) could align the source domains well, then such a mapping aligns a target domain as well. In this paper, we simply take DNNs as feature extractors to relax the requirement of distribution alignment. Specifically, we put forward a novel angular invariance and the accompanied norm shift assumption. Based on the proposed term of invariance, we propose a novel deep DG method called Angular Invariance Domain Generalization Network (AIDGN). The optimization objective of AIDGN is developed with a von-Mises Fisher (vMF) mixture model. Extensive experiments on multiple DG benchmark datasets validate the effectiveness of the proposed AIDGN method.