# Domain Generalization via Optimal Transport with Metric Similarity Learning

arXiv: https://arxiv.org/abs/2007.10573 · HTML: https://mlsanity.com/paper/2007.10573/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2020.

## Built on by (most cited first, 27 of 27)

- [DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations](https://mlsanity.com/paper/2201.09637/) (2022)
- [Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification](https://mlsanity.com/paper/2209.01634/) (2022)
- [Language-aware Domain Generalization Network for Cross-Scene Hyperspectral Image Classification](https://mlsanity.com/paper/2209.02700/) (2022)
- [From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2310.20271/) (2023)
- [Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues](https://mlsanity.com/paper/2303.08106/) (2023)
- [Cross-Modal Concept Learning and Inference for Vision-Language Models](https://mlsanity.com/paper/2307.15460/) (2023)
- [Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment](https://mlsanity.com/paper/2301.07845/) (2023)
- [Diverse Target and Contribution Scheduling for Domain Generalization](https://mlsanity.com/paper/2309.16460/) (2023)
- [Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization](https://mlsanity.com/paper/2307.00648/) (2023)
- [Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization](https://mlsanity.com/paper/2106.04923/) (2021)
- [Multi-task Learning by Leveraging the Semantic Information](https://mlsanity.com/paper/2103.02546/) (2021)
- [LICO: Explainable Models with Language-Image Consistency](https://mlsanity.com/paper/2310.09821/) (2023)
- [Gap Minimization for Knowledge Sharing and Transfer](https://mlsanity.com/paper/2201.11231/) (2022)
- [BatStyler: Advancing Multi-category Style Generation for Source-free Domain Generalization](https://mlsanity.com/paper/2501.01109/) (2025)
- [Relating tSNE and UMAP to Classical Dimensionality Reduction](https://mlsanity.com/paper/2306.11898/) (2023)
- [Adversarial and Random Transformations for Robust Domain Adaptation and Generalization](https://mlsanity.com/paper/2211.06788/) (2022)
- [Domain Adversarial Active Learning for Domain Generalization Classification](https://mlsanity.com/paper/2403.06174/) (2024)
- [SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation](https://mlsanity.com/paper/2508.05182/) (2025)
- [Barycentric-alignment and reconstruction loss minimization for domain generalization](https://mlsanity.com/paper/2109.01902/) (2021)
- [Learning Invariant Representations with a Nonparametric Nadaraya-Watson Head](https://mlsanity.com/paper/2309.13377/) (2023)
- [Feature-aligned N-BEATS with Sinkhorn divergence](https://mlsanity.com/paper/2305.15196/) (2023)
- [Domain Generalization for Domain-Linked Classes](https://mlsanity.com/paper/2306.00879/) (2023)
- [DREAM: Domain-free Reverse Engineering Attributes of Black-box Model](https://mlsanity.com/paper/2307.10997/) (2023)
- [ADMEOOD: Out-of-Distribution Benchmark for Drug Property Prediction](https://mlsanity.com/paper/2310.07253/) (2023)
- [DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model](https://mlsanity.com/paper/2412.05842/) (2024)
- [Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach](https://mlsanity.com/paper/2507.12843/) (2025)
- [Invariant Feature Extraction Through Conditional Independence and the Optimal Transport Barycenter Problem: the Gaussian case](https://mlsanity.com/paper/2512.20914/) (2025)

## Abstract (arXiv)

Generalizing knowledge to unseen domains, where data and labels are unavailable, is crucial for machine learning models. We tackle the domain generalization problem to learn from multiple source domains and generalize to a target domain with unknown statistics. The crucial idea is to extract the underlying invariant features across all the domains. Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the label information, which will lead to indistinguishable features with an ambiguous classification boundary. For this, one possible solution is to constrain the label-similarity when extracting the invariant features and to take advantage of the label similarities for class-specific cohesion and separation of features across domains. Therefore we adopt optimal transport with Wasserstein distance, which could constrain the class label similarity, for adversarial training and also further deploy a metric learning objective to leverage the label information for achieving distinguishable classification boundary. Empirical results show that our proposed method could outperform most of the baselines. Furthermore, ablation studies also demonstrate the effectiveness of each component of our method.