arXiv Machine Learning August 26, 2026 By Shizhe Li, Hongshan Pu, Mengying Xie, Yi Xiang, Xiaowei Yang

Joint Distribution Alignment for Universal Domain Adaptation

Read the original on arXiv Machine Learning →

The paper introduces Joint Distribution Alignment for Universal Domain Adaptation (JAUA), a new algorithm designed for scenarios where source and target domains have differing label spaces. It provides a theoretical upper bound on generalization error for Universal Domain Adaptation and proposes aligning joint distributions using Chi‑Square divergence, complemented by a progressive pseudo‑labeling strategy. Experiments on six public image datasets show JAUA outperforms existing methods in handling Universal Domain Adaptation challenges.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 5

Efficient unsupervised domain adaptation via self-supervised vision transformer and synergistic cross-domain alignment

arXiv:2407. 21311v2 Announce Type: replace-cross Abstract: Unsupervised domain adaptation (UDA) aims to mitigate domain shift, where the distribution of labeled source data differs from that of unlabeled target data.

By Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Farhad Pourpanah

llms computer-vision fine-tuning safety

Hugging Face Trending Papers

Jul 22

Variance-reduced Domain Adaptation using Paired Sampling

Correlation alignment and the maximum mean discrepancy are two widely used distribution-matching frameworks for unsupervised domain adaptation (UDA). However, high variance in these losses has been shown to undermine their effectiveness in minibatch optimisation settings.

fine-tuning safety

arXiv Machine Learning

Jul 23

Variance-reduced Domain Adaptation using Paired Sampling

arXiv:2607. 20367v1 Announce Type: new Abstract: Correlation alignment and the maximum mean discrepancy are two widely used distribution-matching frameworks for unsupervised domain adaptation (UDA).

By Andrea Napoli

fine-tuning safety

arXiv Machine Learning

Jun 2

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

arXiv:2606. 00558v1 Announce Type: new Abstract: Transfer learning aims to facilitate the learning of a target domain by transferring knowledge from a source domain.

By Yuan Yao, Jin Song, Huixia Li, Tongtong Yuan, Jiaqi Wu, Yu Zhang

fine-tuning

arXiv Machine Learning

Sep 11

Importance Weighting for Unlabeled-unlabeled Learning under Distribution Shift

This paper introduces a method for adapting unlabeled‑unlabeled (UU) learning to distribution shifts by applying importance weighting. The approach estimates weights from UU data in both training and test distributions to minimize test risk, enabling handling of various learning scenarios—including PU and noisy‑label learning—without assuming specific shift types. Experiments on real‑world datasets confirm the method’s effectiveness.

By Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Taishi Nishiyama, Kazuki Adachi, Yasuhiro Fujiwara

arXiv Machine Learning

Jul 21

LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation

arXiv:2607. 17653v1 Announce Type: cross Abstract: Source-free universal domain adaptation (SF-UniDA) adapts a pre-trained source model to an unlabeled target domain under both covariate and label shifts, without access to source data.

By Jing Li, Pan Liu, Meng Zhao, Wanli Xue, Yanhong Yang, Xu Cheng, Fan Shi, Jianhua Zhang, Qinghua Hu, Shengyong Chen

llms fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

Efficient unsupervised domain adaptation via self-supervised vision transformer and synergistic cross-domain alignment

Variance-reduced Domain Adaptation using Paired Sampling

Variance-reduced Domain Adaptation using Paired Sampling

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

Importance Weighting for Unlabeled-unlabeled Learning under Distribution Shift

LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation