# Computationally Efficient Wasserstein Loss for Structured Labels

Source: [Computationally Efficient Wasserstein Loss for Structured Labels](<https://www.sota2.com/research/paper/68fa69721e209131cea22231>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:00:47.140Z

Authors: Ayato Toyokuni, Sho Yokoi, Hisashi Kashima, Makoto Yamada

Published: 2021-03-01T10:45:13.000Z

## Abstract

The problem of estimating the probability distribution of labels has been widely studied as a label distribution learning (LDL) problem, whose applications include age estimation, emotion analysis, and semantic segmentation. We propose a tree-Wasserstein distance regularized LDL algorithm, focusing on hierarchical text classification tasks. We propose predicting the entire label hierarchy using neural networks, where the similarity between predicted and true labels is measured using the tree-Wasserstein distance. Through experiments using synthetic and real-world datasets, we demonstrate that the proposed method successfully considers the structure of labels during training, and it compares favorably with the Sinkhorn algorithm in terms of computation time and memory usage.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.00899>)

[PDF](<https://arxiv.org/pdf/2103.00899.pdf>)