Novel Loss Functions for Improved Data Visualization in t-SNE

A popular method for projecting high-dimensional data onto a lower-dimensional space while preserving the integrity of its structure is t-distributed Stochastic Neighbor Embedding (t-SNE). This technique minimizes the Kullback–Leibler ((Formula presented.)) divergence to align the similarities between points in the original and reduced spaces. While t-SNE is highly effective, it prioritizes local neighborhood preservation, which results in limited separation between distant clusters and inadequate representation of global relationships. To improve these limitations, this work introduces two complementary approaches: (1) The Max-Flipped (Formula presented.) Divergence ((Formula presented.)) modifies the original divergence by incorporating a contrastive term, (Formula presented.), which enhances the ranking of point similarities through maximum similarity constraints. (2) The (Formula presented.) -Wasserstein Loss ((Formula presented.)) combines the (Formula presented.) divergence with the classic Wasserstein distance, allowing the embedding to benefit from the smooth and geometry-aware transport properties of Wasserstein metrics. Experimental results show that these methods lead to improved separation and better structural clarity in the low-dimensional space compared to standard t-SNE.