Transductive Adversarial Networks (TAN)

02/08/2018
by   Sean Rowan, et al.
0

Transductive Adversarial Networks (TAN) is a novel domain-adaptation machine learning framework that is designed for learning a conditional probability distribution on unlabelled input data in a target domain, while also only having access to: (1) easily obtained labelled data from a related source domain, which may have a different conditional probability distribution than the target domain, and (2) a marginalised prior distribution on the labels for the target domain. TAN leverages a fully adversarial training procedure and a unique generator/encoder architecture which approximates the transductive combination of the available source- and target-domain data. A benefit of TAN is that it allows the distance between the source- and target-domain label-vector marginal probability distributions to be greater than 0 (i.e. different tasks across the source and target domains) whereas other domain-adaptation algorithms require this distance to equal 0 (i.e. a single task across the source and target domains). TAN can, however, still handle the latter case and is a more generalised approach to this case. Another benefit of TAN is that due to being a fully adversarial algorithm, it has the potential to accurately approximate highly complex distributions. Theoretical analysis demonstrates the viability of the TAN framework.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/19/2020

Learning Bounds for Moment-Based Domain Adaptation

Domain adaptation algorithms are designed to minimize the misclassificat...
research
11/15/2022

Dynamic-Pix2Pix: Noise Injected cGAN for Modeling Input and Target Domain Joint Distributions with Limited Training Data

Learning to translate images from a source to a target domain with appli...
research
10/14/2019

Wasserstein Distance Guided Cross-Domain Learning

Domain adaptation aims to generalise a high-performance learner on targe...
research
01/01/2017

Aspect-augmented Adversarial Networks for Domain Adaptation

We introduce a neural method for transfer learning between two (source a...
research
05/24/2020

Discriminative Active Learning for Domain Adaptation

Domain Adaptation aiming to learn a transferable feature between differe...
research
08/17/2021

Direct domain adaptation through reciprocal linear transformations

We propose a direct domain adaptation (DDA) approach to enrich the train...
research
10/08/2019

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