<ul><li>Aggregating data from multiple sources can be formalized as an Optimal Transport (OT) barycenter problem.</li><li>A novel scalable approach is proposed for estimating robust continuous barycenter, leveraging the dual formulation of the (semi-)unbalanced OT problem.</li><li>The method is adaptable to general cost functions and demonstrates robustness to outliers and class imbalance.</li><li>Source code for the method is publicly available on GitHub.</li></ul>

Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport

Discover more