DeepAI AI Chat
Log In Sign Up

Knothe-Rosenblatt transport for Unsupervised Domain Adaptation

by   Aladin Virmaux, et al.

Unsupervised domain adaptation (UDA) aims at exploiting related but different data sources to tackle a common task in a target domain. UDA remains a central yet challenging problem in machine learning. In this paper, we present an approach tailored to moderate-dimensional tabular problems which are hugely important in industrial applications and less well-served by the plethora of methods designed for image and language data. Knothe-Rosenblatt Domain Adaptation (KRDA) is based on the Knothe-Rosenblatt transport: we exploit autoregressive density estimation algorithms to accurately model the different sources by an autoregressive model using a mixture of Gaussians. KRDA then takes advantage of the triangularity of the autoregressive models to build an explicit mapping of the source samples into the target domain. We show that the transfer map built by KRDA preserves each component quantiles of the observations, hence aligning the representations of the different data sets in the same target domain. Finally, we show that KRDA has state-of-the-art performance on both synthetic and real world UDA problems.


page 1

page 2

page 3

page 4


Multi-source Attention for Unsupervised Domain Adaptation

Domain adaptation considers the problem of generalising a model learnt u...

AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows

Given unpaired data from multiple domains, a key challenge is to efficie...

Aggregating From Multiple Target-Shifted Sources

Multi-source domain adaptation aims at leveraging the knowledge from mul...

Improve Unsupervised Domain Adaptation with Mixup Training

Unsupervised domain adaptation studies the problem of utilizing a releva...

Learning to smell for wellness

Learning to automatically perceive smell is becoming increasingly import...

Unsupervised Domain Adaptation: A Reality Check

Interest in unsupervised domain adaptation (UDA) has surged in recent ye...

Unsupervised Domain Adaptation Learning for Hierarchical Infant Pose Recognition with Synthetic Data

The Alberta Infant Motor Scale (AIMS) is a well-known assessment scheme ...