# Multiple Source Domain Adaptation with Adversarial Training of Neural Networks

arXiv: https://arxiv.org/abs/1705.09684 · HTML: https://mlsanity.com/paper/1705.09684/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2017.

## Built on by (most cited first, 10 of 10)

- [Conditional Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/2102.10176/) (2021)
- [Co-Regularized Adversarial Learning for Multi-Domain Text Classification](https://mlsanity.com/paper/2201.12796/) (2022)
- [MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds](https://mlsanity.com/paper/2304.01554/) (2023)
- [Multi-Source Survival Domain Adaptation](https://mlsanity.com/paper/2212.00424/) (2022)
- [FACT: Federated Adversarial Cross Training](https://mlsanity.com/paper/2306.00607/) (2023)
- [Margin Discrepancy-based Adversarial Training for Multi-Domain Text Classification](https://mlsanity.com/paper/2403.00888/) (2024)
- [Stochastic Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/2406.00044/) (2024)
- [Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge](https://mlsanity.com/paper/2105.11902/) (2021)
- [Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift](https://mlsanity.com/paper/2405.19156/) (2024)
- [ALIGN: Adversarial Learning for Generalizable Speech Neuroprosthesis](https://mlsanity.com/paper/2603.18299/) (2026)

## Abstract (arXiv)

While domain adaptation has been actively researched in recent years, most theoretical results and algorithms focus on the single-source-single-target adaptation setting. Naive application of such algorithms on multiple source domain adaptation problem may lead to suboptimal solutions. As a step toward bridging the gap, we propose a new generalization bound for domain adaptation when there are multiple source domains with labeled instances and one target domain with unlabeled instances. Compared with existing bounds, the new bound does not require expert knowledge about the target distribution, nor the optimal combination rule for multisource domains. Interestingly, our theory also leads to an efficient learning strategy using adversarial neural networks: we show how to interpret it as learning feature representations that are invariant to the multiple domain shifts while still being discriminative for the learning task. To this end, we propose two models, both of which we call multisource domain adversarial networks (MDANs): the first model optimizes directly our bound, while the second model is a smoothed approximation of the first one, leading to a more data-efficient and task-adaptive model. The optimization tasks of both models are minimax saddle point problems that can be optimized by adversarial training. To demonstrate the effectiveness of MDANs, we conduct extensive experiments showing superior adaptation performance on three real-world datasets: sentiment analysis, digit classification, and vehicle counting.