# Domain Adaptation via Maximizing Surrogate Mutual Information

arXiv: https://arxiv.org/abs/2110.12184 · HTML: https://mlsanity.com/paper/2110.12184/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 23 Oct 2021.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Progressive Feature Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.08585/) (2018)
- [A survey on domain adaptation theory: learning bounds and theoretical guarantees](https://mlsanity.com/paper/2004.11829/) (2020)
- [Discriminative Adversarial Domain Adaptation](https://mlsanity.com/paper/1911.12036/) (2019)
- [Adversarial-Learned Loss for Domain Adaptation](https://mlsanity.com/paper/2001.01046/) (2020)
- [Domain Conditioned Adaptation Network](https://mlsanity.com/paper/2005.06717/) (2020)
- [Contrastive Domain Adaptation](https://mlsanity.com/paper/2103.15566/) (2021)
- [Joint Contrastive Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2006.10297/) (2020)
- [Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment](https://mlsanity.com/paper/2002.08675/) (2020)

## Built on by (most cited first, 8 of 8)

- [Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand](https://mlsanity.com/paper/2310.14942/) (2023)
- [KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models](https://mlsanity.com/paper/2402.02801/) (2024)
- [Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation](https://mlsanity.com/paper/2110.12648/) (2021)
- [IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Method](https://mlsanity.com/paper/2410.00059/) (2024)
- [Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information](https://mlsanity.com/paper/2603.03725/) (2026)
- [Causal Domain Adaptation with Copula Entropy based Conditional Independence Test](https://mlsanity.com/paper/2202.13482/) (2022)
- [Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation](https://mlsanity.com/paper/2508.09223/) (2025)
- [Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiency](https://mlsanity.com/paper/2508.18693/) (2025)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) aims to predict unlabeled data from target domain with access to labeled data from the source domain. In this work, we propose a novel framework called SIDA (Surrogate Mutual Information Maximization Domain Adaptation) with strong theoretical guarantees. To be specific, SIDA implements adaptation by maximizing mutual information (MI) between features. In the framework, a surrogate joint distribution models the underlying joint distribution of the unlabeled target domain. Our theoretical analysis validates SIDA by bounding the expected risk on target domain with MI and surrogate distribution bias. Experiments show that our approach is comparable with state-of-the-art unsupervised adaptation methods on standard UDA tasks.