Knowledge Adaptation: Teaching to Adapt

TL;DR

This paper introduces Knowledge Adaptation, a novel extension of Knowledge Distillation, enabling effective unsupervised domain adaptation by leveraging multiple teachers and domain similarity metrics, achieving state-of-the-art results in sentiment analysis.

Contribution

It proposes a new method for domain adaptation using Knowledge Distillation with multiple teachers and a domain similarity metric, addressing limitations of previous joint training approaches.

Findings

Achieves state-of-the-art results on sentiment analysis benchmark.

Effectively leverages multiple teachers for domain adaptation.

Uses a domain similarity metric to select high-confidence examples.

Abstract

Domain adaptation is crucial in many real-world applications where the distribution of the training data differs from the distribution of the test data. Previous Deep Learning-based approaches to domain adaptation need to be trained jointly on source and target domain data and are therefore unappealing in scenarios where models need to be adapted to a large number of domains or where a domain is evolving, e.g. spam detection where attackers continuously change their tactics. To fill this gap, we propose Knowledge Adaptation, an extension of Knowledge Distillation (Bucilua et al., 2006; Hinton et al., 2015) to the domain adaptation scenario. We show how a student model achieves state-of-the-art results on unsupervised domain adaptation from multiple sources on a standard sentiment analysis benchmark by taking into account the domain-specific expertise of multiple teachers and the similarities between their domains. When learning from a single teacher, using domain similarity to gauge trustworthiness is inadequate. To this end, we propose a simple metric that correlates well with the teacher's accuracy in the target domain. We demonstrate that incorporating high-confidence examples selected by this metric enables the student model to achieve state-of-the-art performance in the single-source scenario.