# Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space

arXiv: https://arxiv.org/abs/2307.14953 · HTML: https://mlsanity.com/paper/2307.14953/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 54 references that are in the map.
- First posted on arXiv 27 Jul 2023.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [Fast Computation of Wasserstein Barycenters](https://mlsanity.com/paper/1310.4375/) (2013)
- [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018)
- [Geometric Dataset Distances via Optimal Transport](https://mlsanity.com/paper/2002.02923/) (2020)
- [A survey on domain adaptation theory: learning bounds and theoretical guarantees](https://mlsanity.com/paper/2004.11829/) (2020)
- [Theoretical Analysis of Domain Adaptation with Optimal Transport](https://mlsanity.com/paper/1610.04420/) (2016)
- [Learning with minibatch Wasserstein : asymptotic and gradient properties](https://mlsanity.com/paper/1910.04091/) (2019)
- [Recent Advances in Optimal Transport for Machine Learning](https://mlsanity.com/paper/2306.16156/) (2023)
- [Minibatch optimal transport distances; analysis and applications](https://mlsanity.com/paper/2101.01792/) (2021)
- [Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2007.08801/) (2020)
- [Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning](https://mlsanity.com/paper/1708.01955/) (2017)
- [Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transport](https://mlsanity.com/paper/2006.12938/) (2020)

## Built on by (most cited first, 12 of 12)

- [Multi-Source Domain Adaptation meets Dataset Distillation through Dataset Dictionary Learning](https://mlsanity.com/paper/2309.07666/) (2023)
- [Lighter, Better, Faster Multi-Source Domain Adaptation with Gaussian Mixture Models and Optimal Transport](https://mlsanity.com/paper/2404.10261/) (2024)
- [Benchmarking Domain Adaptation for Chemical Processes on the Tennessee Eastman Process](https://mlsanity.com/paper/2308.11247/) (2023)
- [Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2309.07670/) (2023)
- [Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains](https://mlsanity.com/paper/2402.14145/) (2024)
- [Optimal Transport for Domain Adaptation through Gaussian Mixture Models](https://mlsanity.com/paper/2403.13847/) (2024)
- [Dataset Dictionary Learning in a Wasserstein Space for Federated Domain Adaptation](https://mlsanity.com/paper/2407.11647/) (2024)
- [Online Multi-Source Domain Adaptation through Gaussian Mixtures and Dataset Dictionary Learning](https://mlsanity.com/paper/2407.19853/) (2024)
- [FoCTTA: Low-Memory Continual Test-Time Adaptation with Focus](https://mlsanity.com/paper/2502.20677/) (2025)
- [KD2M: A unifying framework for feature knowledge distillation](https://mlsanity.com/paper/2504.01757/) (2025)
- [DeFed-GMM-DaDiL: A Decentralized Federated Framework for Domain Adaptation](https://mlsanity.com/paper/2605.04324/) (2026)
- [Towards Universal Wasserstein Barycenters through Flow Matching](https://mlsanity.com/paper/2609.38547/) (2026)

## Abstract (arXiv)

This paper seeks to solve Multi-Source Domain Adaptation (MSDA), which aims to mitigate data distribution shifts when transferring knowledge from multiple labeled source domains to an unlabeled target domain. We propose a novel MSDA framework based on dictionary learning and optimal transport. We interpret each domain in MSDA as an empirical distribution. As such, we express each domain as a Wasserstein barycenter of dictionary atoms, which are empirical distributions. We propose a novel algorithm, DaDiL, for learning via mini-batches: (i) atom distributions; (ii) a matrix of barycentric coordinates. Based on our dictionary, we propose two novel methods for MSDA: DaDil-R, based on the reconstruction of labeled samples in the target domain, and DaDiL-E, based on the ensembling of classifiers learned on atom distributions. We evaluate our methods in 3 benchmarks: Caltech-Office, Office 31, and CRWU, where we improved previous state-of-the-art by 3.15%, 2.29%, and 7.71% in classification performance. Finally, we show that interpolations in the Wasserstein hull of learned atoms provide data that can generalize to the target domain.