# Dual Supervised Learning

arXiv: https://arxiv.org/abs/1707.00415 · HTML: https://mlsanity.com/paper/1707.00415/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2017.

## Built on by (most cited first, 30 of 33)

- [Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation](https://mlsanity.com/paper/2203.16586/) (2022)
- [Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks](https://mlsanity.com/paper/2107.01431/) (2021)
- [Modeling Dual Read/Write Paths for Simultaneous Machine Translation](https://mlsanity.com/paper/2203.09163/) (2022)
- [LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification](https://mlsanity.com/paper/2106.01649/) (2021)
- [There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory](https://mlsanity.com/paper/2204.02624/) (2022)
- [DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms](https://mlsanity.com/paper/2406.07232/) (2024)
- [Towards Lightweight Super-Resolution with Dual Regression Learning](https://mlsanity.com/paper/2207.07929/) (2022)
- [Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations](https://mlsanity.com/paper/2104.08490/) (2021)
- [Duplex Sequence-to-Sequence Learning for Reversible Machine Translation](https://mlsanity.com/paper/2105.03458/) (2021)
- [An Information Retrieval Approach to Building Datasets for Hate Speech Detection](https://mlsanity.com/paper/2106.09775/) (2021)
- [Recommender systems based on graph embedding techniques: A comprehensive review](https://mlsanity.com/paper/2109.09587/) (2021)
- [SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards](https://mlsanity.com/paper/2506.07963/) (2025)
- [Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation](https://mlsanity.com/paper/2303.11180/) (2023)
- [Typo-Robust Representation Learning for Dense Retrieval](https://mlsanity.com/paper/2306.10348/) (2023)
- [DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation](https://mlsanity.com/paper/2212.08724/) (2022)
- [Interactive Molecular Discovery with Natural Language](https://mlsanity.com/paper/2306.11976/) (2023)
- [On the Generative Utility of Cyclic Conditionals](https://mlsanity.com/paper/2106.15962/) (2021)
- [Unsupervised Sign Language Translation and Generation](https://mlsanity.com/paper/2402.07726/) (2024)
- [Multi-Party Dual Learning](https://mlsanity.com/paper/2104.06677/) (2021)
- [Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels](https://mlsanity.com/paper/2104.07283/) (2021)
- [Dual Learning Music Composition and Dance Choreography](https://mlsanity.com/paper/2201.11999/) (2022)
- [Dual Task Framework for Improving Persona-grounded Dialogue Dataset](https://mlsanity.com/paper/2202.05435/) (2022)
- [Deep Compatible Learning for Partially-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2206.09148/) (2022)
- [Text Style Transfer Back-Translation](https://mlsanity.com/paper/2306.01318/) (2023)
- [DualTalker: A Cross-Modal Dual Learning Approach for Speech-Driven 3D Facial Animation](https://mlsanity.com/paper/2311.04766/) (2023)
- [The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation](https://mlsanity.com/paper/2403.18031/) (2024)
- [Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs](https://mlsanity.com/paper/2510.01527/) (2025)
- [Verdi: Quality Estimation and Error Detection for Bilingual Corpora](https://mlsanity.com/paper/2105.14878/) (2021)
- [Multijugate Dual Learning for Low-Resource Task-Oriented Dialogue System](https://mlsanity.com/paper/2305.16106/) (2023)
- [Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image](https://mlsanity.com/paper/2410.15312/) (2024)

## Abstract (arXiv)

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 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.