Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization

Learning conditional distributions $\pi^*(\cdot|x)$ is a central problem in machine learning, which is typically approached via supervised methods with paired data $(x,y) \sim \pi^*$. However, acquiring paired data samples is often challenging, especially in problems such as domain translation. This necessitates the development of $\textit{semi-supervised}$ models that utilize both limited paired data and additional unpaired i.i.d. samples $x \sim \pi^*_x$ and $y \sim \pi^*_y$ from the marginal distributions. The usage of such combined data is complex and often relies on heuristic approaches. To tackle this issue, we propose a new learning paradigm that integrates both paired and unpaired data $\textbf{seamlessly}$ through the data likelihood maximization techniques. We demonstrate that our approach also connects intriguingly with inverse entropic optimal transport (OT). This finding allows us to apply recent advances in computational OT to establish a $\textbf{light}$ learning algorithm to get $\pi^*(\cdot|x)$. Furthermore, we demonstrate through empirical tests that our method effectively learns conditional distributions using paired and unpaired data simultaneously.

@article{persiianov2025_2410.02628,
  title={ Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization },
  author={ Mikhail Persiianov and Arip Asadulaev and Nikita Andreev and Nikita Starodubcev and Dmitry Baranchuk and Anastasis Kratsios and Evgeny Burnaev and Alexander Korotin },
  journal={arXiv preprint arXiv:2410.02628},
  year={ 2025 }
}