Abstract

We develop an algorithm to improve the predictive performance of a pre-trained model under\textit {concept shift} without retraining the model from scratch when only unannotated samples of initial concepts are accessible. We model this problem as a domain adaptation problem, where the source domain data is inaccessible during model adaptation. The core idea is based on consolidating the intermediate internal distribution, learned to represent the source domain data, after adapting the model. We provide theoretical analysis and conduct extensive experiments on five benchmark datasets to demonstrate that the proposed method is effective.

Date

February 15, 2023

Authors

Mohammad Rostami, Aram Galstyan

Conference

Thirty-Seventh AAAI Conference on Artificial Intelligence

Publisher

https://arxiv.org/pdf/2007.00197.pdf