Dual Supervised Learning

TL;DR

This paper introduces dual supervised learning, a method that simultaneously trains dual tasks by leveraging their probabilistic correlation, leading to improved performance across various applications.

Contribution

It proposes a novel dual supervised learning framework that explicitly exploits the probabilistic connection between dual tasks during training.

Findings

Improved performance in machine translation, image processing, and sentiment analysis.

Effective regularization of models through dual task correlation.

Demonstrated benefits over separate training approaches.

Abstract

Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have intrinsic connections with each other due to the probabilistic correlation between their models. This connection is, however, not effectively utilized today, since people usually train the models of two dual tasks separately and independently. In this work, we propose training the models of two dual tasks simultaneously, and explicitly exploiting the probabilistic correlation between them to regularize the training process. For ease of reference, we call the proposed approach \emph{dual supervised learning}. We demonstrate that dual supervised learning can improve the practical performances of both tasks, for various applications including machine translation, image processing, and sentiment analysis.