Recent advances in optimal transport for machine learning

EF Montesuma, FMN Mboula… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recently, Optimal Transport has been proposed as a probabilistic framework in Machine
Learning for comparing and manipulating probability distributions. This is rooted in its rich …

Lamda: Label matching deep domain adaptation

T Le, T Nguyen, N Ho, H Bui… - … Conference on Machine …, 2021 - proceedings.mlr.press
Deep domain adaptation (DDA) approaches have recently been shown to perform better
than their shallow rivals with better modeling capacity on complex domains (eg, image …

Stem: An approach to multi-source domain adaptation with guarantees

VA Nguyen, T Nguyen, T Le… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract Multi-source Domain Adaptation (MSDA) is more practical but challenging than the
conventional unsupervised domain adaptation due to the involvement of diverse multiple …

Your data is not perfect: Towards cross-domain out-of-distribution detection in class-imbalanced data

X Fang, A Easwaran, B Genest… - Expert Systems with …, 2025 - Elsevier
Out-of-distribution detection (OOD detection) aims to detect test samples drawn from a
distribution that is different from the training distribution, in order to prevent models trained …

Transformed distribution matching for missing value imputation

H Zhao, K Sun, A Dezfouli… - … Conference on Machine …, 2023 - proceedings.mlr.press
We study the problem of imputing missing values in a dataset, which has important
applications in many domains. The key to missing value imputation is to capture the data …

A unified wasserstein distributional robustness framework for adversarial training

TA Bui, T Le, Q Tran, H Zhao, D Phung - arxiv preprint arxiv:2202.13437, 2022 - arxiv.org
It is well-known that deep neural networks (DNNs) are susceptible to adversarial attacks,
exposing a severe fragility of deep learning systems. As the result, adversarial training (AT) …

Distribution alignment optimization through neural collapse for long-tailed classification

J Gao, H Zhao, D dan Guo, H Zha - Forty-first International …, 2024 - openreview.net
A well-trained deep neural network on balanced datasets usually exhibits the Neural
Collapse (NC) phenomenon, which is an informative indicator of the model achieving good …

MANNER: A variational memory-augmented model for cross domain few-shot named entity recognition

J Fang, X Wang, Z Meng, P **e, F Huang… - Proceedings of the …, 2023 - aclanthology.org
This paper focuses on the task of cross domain few-shot named entity recognition (NER),
which aims to adapt the knowledge learned from source domain to recognize named entities …

Tuning multi-mode token-level prompt alignment across modalities

D Wang, M Li, X Liu, MS Xu… - Advances in Neural …, 2024 - proceedings.neurips.cc
Advancements in prompt tuning of vision-language models have underscored their potential
in enhancing open-world visual concept comprehension. However, prior works only …

Tidot: A teacher imitation learning approach for domain adaptation with optimal transport

T Nguyen, T Le, N Dam, QH Tran… - … Joint Conference on …, 2021 - research.monash.edu
Using the principle of imitation learning and the theory of optimal transport we propose in
this paper a novel model for unsupervised domain adaptation named Teacher Imitation …