Pre-Trained Model Reusability Evaluation for Small-Data Transfer Learning

Yao-Xiang Ding, Xi-Zhu Wu, Kun Zhou, Zhi-Hua Zhou

Keywords: transfer learning, metric learning, meta-learning

TL;DR: We propose a metric-based approach named synergistic learning for evaluating pre-trained model reusability with small data.

Abstract: We study {\it model reusability evaluation} (MRE) for source pre-trained models: evaluating their transfer learning performance to new target tasks. In special, we focus on the setting under which the target training datasets are small, making it difficult to produce reliable MRE scores using them. Under this situation, we propose {\it synergistic learning} for building the task-model metric, which can be realized by collecting a set of pre-trained models and asking a group of data providers to participate. We provide theoretical guarantees to show that the learned task-model metric distances can serve as trustworthy MRE scores, and propose synergistic learning algorithms and models for general learning tasks. Experiments show that the MRE models learned by synergistic learning can generate significantly more reliable MRE scores than existing approaches for small-data transfer learning.