Frustratingly Easy Transferability Estimation
arXiv:2106.09362
Abstract
Transferability estimation has been an essential tool in selecting a pre-trained model and the layers in it for transfer learning, to transfer, so as to maximize the performance on a target task and prevent negative transfer. Existing estimation algorithms either require intensive training on target tasks or have difficulties in evaluating the transferability between layers. To this end, we propose a simple, efficient, and effective transferability measure named TransRate. Through a single pass over examples of a target task, TransRate measures the transferability as the mutual information between features of target examples extracted by a pre-trained model and their labels. We overcome the challenge of efficient mutual information estimation by resorting to coding rate that serves as an effective alternative to entropy. From the perspective of feature representation, the resulting TransRate evaluates both completeness (whether features contain sufficient information of a target task) and compactness (whether features of each class are compact enough for good generalization) of pre-trained features. Theoretically, we have analyzed the close connection of TransRate to the performance after transfer learning. Despite its extraordinary simplicity in 10 lines of codes, TransRate performs remarkably well in extensive evaluations on 32 pre-trained models and 16 downstream tasks.
arXiv commentAccepted by ICML 2022
References in corpus (9)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Estimating Mutual Information
- How transferable are features in deep neural networks?
- Learning deep representations by mutual information estimation and maximization
- Fine-Grained Visual Classification of Aircraft
- LEEP: A New Measure to Evaluate Transferability of Learned Representations
- LogME: Practical Assessment of Pre-trained Models for Transfer Learning
- Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
- A linearized framework and a new benchmark for model selection for fine-tuning