Pith. sign in

Knowledge Adaptation: Teaching to Adapt

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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.

citation-role summary

background 1

citation-polarity summary

fields

cs.RO 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

support 1

representative citing papers

CARoL: Context-aware Adaptation for Robot Learning

cs.RO · 2025-06-08 · conditional · novelty 6.0

CARoL measures task similarity by state-transition prediction errors and uses those similarities to weight prior policies, value functions, or actor-critic knowledge when adapting to a new task.

citing papers explorer

Showing 1 of 1 citing paper.

  • CARoL: Context-aware Adaptation for Robot Learning cs.RO · 2025-06-08 · conditional · none · ref 24 · internal anchor

    CARoL measures task similarity by state-transition prediction errors and uses those similarities to weight prior policies, value functions, or actor-critic knowledge when adapting to a new task.