Saved in:
Bibliographic Details
Main Authors: Saoud, Abdel Djalil Sad, Mboula, Fred Maurice Ngolè, Slimani, Hanane
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.13350
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914374275301376
author Saoud, Abdel Djalil Sad
Mboula, Fred Maurice Ngolè
Slimani, Hanane
author_facet Saoud, Abdel Djalil Sad
Mboula, Fred Maurice Ngolè
Slimani, Hanane
contents Distributional shifts between training and inference time data remain a central challenge in machine learning, often leading to poor performance. It motivated the study of principled approaches for domain alignment, such as optimal transport based unsupervised domain adaptation, that relies on approximating Monge map using transport plans, which is sensitive to the transport problem regularization strategy and hyperparameters, and might yield biased domains alignment. In this work, we propose to interpret smoothed transport plans as adjacency matrices of bipartite graphs connecting source to target domain and derive domain-invariant samples' representations through spectral embedding. We evaluate our approach on acoustic adaptation benchmarks for music genre recognition, music-speech discrimination, as well as electrical cable defect detection and classification tasks using time domain reflection in different diagnosis settings, achieving overall strong performances.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13350
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Mapping : Domain-Invariant Representations via Spectral Embedding of Optimal Transport Plans
Saoud, Abdel Djalil Sad
Mboula, Fred Maurice Ngolè
Slimani, Hanane
Machine Learning
Distributional shifts between training and inference time data remain a central challenge in machine learning, often leading to poor performance. It motivated the study of principled approaches for domain alignment, such as optimal transport based unsupervised domain adaptation, that relies on approximating Monge map using transport plans, which is sensitive to the transport problem regularization strategy and hyperparameters, and might yield biased domains alignment. In this work, we propose to interpret smoothed transport plans as adjacency matrices of bipartite graphs connecting source to target domain and derive domain-invariant samples' representations through spectral embedding. We evaluate our approach on acoustic adaptation benchmarks for music genre recognition, music-speech discrimination, as well as electrical cable defect detection and classification tasks using time domain reflection in different diagnosis settings, achieving overall strong performances.
title Beyond Mapping : Domain-Invariant Representations via Spectral Embedding of Optimal Transport Plans
topic Machine Learning
url https://arxiv.org/abs/2601.13350