Overcoming Concept Shift in Domain-Aware Settings through Consolidated Internal Distributions

1 Jul 2020  ·  Mohammad Rostami, Aram Galstyan ·

We develop an algorithm to improve the performance of a pre-trained model under 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 to demonstrate that the proposed method is effective.

PDF Abstract

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here