Improved Regularization and Robustness for Fine-tuning in Neural Networks

Abstract

A widely used algorithm for transfer learning is fine-tuning, where a pre-trained model is fine-tuned on a target task with a small amount of labeled data. When the capacity of the pre-trained model is much larger than the size of the target data set, fine-tuning is prone to overfitting and "memorizing" the training labels. Hence, an important question is to regularize fine-tuning and ensure its robustness to noise. To address this question, we begin by analyzing the generalization properties of fine-tuning. We present a PAC-Bayes generalization bound that depends on the distance traveled in each layer during fine-tuning and the noise stability of the fine-tuned model. We empirically measure these quantities. Based on the analysis, we propose regularized self-labeling-the interpolation between regularization and self-labeling methods, including (i) layer-wise regularization to constrain the distance traveled in each layer; (ii) self label-correction and label-reweighting to correct mislabeled data points (that the model is confident) and reweight less confident data points. We validate our approach on an extensive collection of image and text data sets using multiple pre-trained model architectures. Our approach improves baseline methods by 1.76% (on average) for seven image classification tasks and 0.75% for a few-shot classification task. When the target data set includes noisy labels, our approach outperforms baseline methods by 3.56% on average in two noisy settings.35th Conference on Neural Information Processing Systems (NeurIPS 2021).

A Survey on Deep Transfer Learning and Beyond

“…Model-Based DTL Fine-Tuning [43,[45][46][47][48][49][50] Self-Training [51][52][53] Transformer Mechanism [54][55][56][57][58] Share and fine-tune the parameters of deep learning models Discrepancy-Based DTL Dual-Stream Architecture [59][60][61][62][63][64][65][66][67][68][69][70][71][72] Operate on Image Features [73][74][75] Reduce feature discrepancies between source and target domains by DNN GAN-Based DTL Feature Extraction [76][77][78][79][80][81] Feature Transformation [82][83][84][85][86][87][88][89][90] Extract domain invariant features by generative adversarial networks Relational-Based DTL Cross-Domain Relationship …”

“…One is the fine-tuning model. which fine-tunes the parameters of source-domain networks to achieve good performance in target domains [43,[45][46][47][48][49][50]. The second is the self-training approach, which is adopted to overcome the limitations of the fine-tuning model in the case of data enhancement and annotation increases [51][52][53].…”

“…The latest fine-tuning research addresses the overfitting problem when the number of target datasets is small. Li et al [50] proposed to interpolate between regularization and self-labeling, including layer-wise regularization, self label-correction, and label re-weighting.…”