arXiv Machine Learning

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.

arXiv Machine Learning

Aug 26

Joint Distribution Alignment for Universal Domain Adaptation

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.

By Shizhe Li, Hongshan Pu, Mengying Xie, Yi Xiang, Xiaowei Yang

computer-vision fine-tuning safety

arXiv Machine Learning

Jul 8

Factorizable joint shift revisited

arXiv:2601. 15036v4 Announce Type: replace Abstract: Factorizable joint shift (FJS) represents a type of distribution shift (or dataset shift) that comprises both covariate and label shift.

By Dirk Tasche

arXiv Machine Learning

Sep 11

General Quantification of Covariate and Concept Shifts

arXiv:2609. 11918v1 Announce Type: new Abstract: Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples.

By Hongbo Chen, Li Charlie Xia

arXiv AI

Aug 18

DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations

arXiv:2405. 07780v3 Announce Type: replace-cross Abstract: This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced.

By Zhiyong Yang, Qianqian Xu, Sicong Li, Zitai Wang, Xiaochun Cao, Qingming Huang

fine-tuning

arXiv AI

Sep 1

Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning

arXiv:2608.30699v1 Announce Type: cross Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to...

By Yue Cheng, Jiajun Zhang, Xiaohui Gao, Weiwei Xing, Zhanxing Zhu

efficiency benchmarks safety

arXiv Machine Learning

Aug 26

From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift

arXiv:2605.31187v2 Announce Type: replace-cross Abstract: Detecting covariate shift is critical for building reliable vision systems. While most prior work focuses on improving robustness to shift, e...

By Firas Gabetni, Alexandre Rocchi, Nacim Belkhir, Ziyi Liu, Gianni Franchi

arXiv Machine Learning

Sep 15

Learning under Target Shift: Optimal Density Ratio Estimation and Importance-Weighted Regression

arXiv:2609.15785v1 Announce Type: cross Abstract: We study density ratio estimation and importance-weighted regression under target shift with continuous outputs. Under target shift, the conditional...

By Ren-Rui Liu, Zheng-Chu Guo

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 AI

Jul 15

Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite

arXiv:2607. 11947v1 Announce Type: cross Abstract: Typical semi-supervised learning (SSL) methods rely on distributional assumptions, and their performance degrades when these are violated.

By Yushi Hirose, Hiroo Irobe, Takafumi Kanamori

benchmarks

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

arXiv Machine Learning

Aug 4

Augmented Inverse Hybrid Weighting: Robust Inference under Deterministic and Random Distribution Shifts

arXiv:2608. 00701v1 Announce Type: cross Abstract: Reweighting source samples to match a target covariate distribution is a standard response to distribution shift when generalizing evidence from one population to another.

By Ying Jin, Ying Jin, Dominik Rothenh\"ausler

safety

arXiv Machine Learning

Aug 14

Statistical Properties of Robust Learning under Distributional Shifts

arXiv:2608. 13133v1 Announce Type: cross Abstract: Distributional shifts arise when the target deployment environment differs from the source environment that generated the training data.

By Zhiyi Li, Xiaojie Mao, Yunbei Xu, Ruohan Zhan

safety

Related stories