Disjoint Label Space Transfer Learning with Common Factorised Space

by   Xiaobin Chang, et al.
Queen Mary University of London

In this paper, a unified approach is presented to transfer learning that addresses several source and target domain label-space and annotation assumptions with a single model. It is particularly effective in handling a challenging case, where source and target label-spaces are disjoint, and outperforms alternatives in both unsupervised and semi-supervised settings. The key ingredient is a common representation termed Common Factorised Space. It is shared between source and target domains, and trained with an unsupervised factorisation loss and a graph-based loss. With a wide range of experiments, we demonstrate the flexibility, relevance and efficacy of our method, both in the challenging cases with disjoint label spaces, and in the more conventional cases such as unsupervised domain adaptation, where the source and target domains share the same label-sets.


FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) methods for learning domain invaria...

Unveiling Class-Labeling Structure for Universal Domain Adaptation

As a more practical setting for unsupervised domain adaptation, Universa...

IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation

Distribution shift between train (source) and test (target) datasets is ...

Aspect-augmented Adversarial Networks for Domain Adaptation

We introduce a neural method for transfer learning between two (source a...

Unsupervised Domain Adaptation: An Adaptive Feature Norm Approach

Unsupervised domain adaptation aims to mitigate the domain shift when tr...

Domain Adaptation on Graphs by Learning Aligned Graph Bases

We propose a method for domain adaptation on graphs. Given sufficiently ...

ATL: Autonomous Knowledge Transfer from Many Streaming Processes

Transferring knowledge across many streaming processes remains an unchar...

Please sign up or login with your details

Forgot password? Click here to reset