English
Related papers

Related papers: Limitations of Post-Hoc Feature Alignment for Robu…

200 papers

Training deep neural networks with only a few labeled samples can lead to overfitting. This is problematic in semi-supervised learning where only a few labeled samples are available. In this paper, we show that a consequence of overfitting…

Computer Vision and Pattern Recognition · Computer Science 2019-12-24 Christoph Mayer , Matthieu Paul , Radu Timofte

While statistics and machine learning offers numerous methods for ensuring generalization, these methods often fail in the presence of adaptivity---the common practice in which the choice of analysis depends on previous interactions with…

Machine Learning · Computer Science 2018-06-19 Kobbi Nissim , Adam Smith , Thomas Steinke , Uri Stemmer , Jonathan Ullman

A key challenge in training Large Language Models (LLMs) is properly aligning them with human preferences. Reinforcement Learning with Human Feedback (RLHF) uses pairwise comparisons from human annotators to train reward functions and has…

Machine Learning · Computer Science 2025-01-17 Ariel D. Procaccia , Benjamin Schiffer , Shirley Zhang

For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statistics. However, the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Guoqiang Wei , Cuiling Lan , Wenjun Zeng , Zhibo Chen

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching…

Machine Learning · Computer Science 2018-11-20 Jun Wen , Risheng Liu , Nenggan Zheng , Qian Zheng , Zhefeng Gong , Junsong Yuan

Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, the phenomenon of robust overfitting, i.e., the robustness starts to decrease significantly…

Machine Learning · Computer Science 2021-12-23 Jihoon Tack , Sihyun Yu , Jongheon Jeong , Minseon Kim , Sung Ju Hwang , Jinwoo Shin

Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we reveal a surprising…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Yanyun Wang , Qingqing Ye , Li Liu , Zi Liang , Haibo Hu

The label shift problem refers to the supervised learning setting where the train and test label distributions do not match. Existing work addressing label shift usually assumes access to an \emph{unlabelled} test sample. This sample may be…

Machine Learning · Computer Science 2021-08-18 Jingzhao Zhang , Aditya Menon , Andreas Veit , Srinadh Bhojanapalli , Sanjiv Kumar , Suvrit Sra

This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when data is limited. The method builds on a base loss function…

Computation and Language · Computer Science 2025-06-03 Hongye Zheng , Yichen Wang , Ray Pan , Guiran Liu , Binrong Zhu , Hanlu Zhang

Unsupervised domain adaptive classifcation intends to improve the classifcation performance on unlabeled target domain. To alleviate the adverse effect of domain shift, many approaches align the source and target domains in the feature…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Guoqiang Wei , Cuiling Lan , Wenjun Zeng , Zhizheng Zhang , Zhibo Chen

Few-shot image classification aims at training a model from only a few examples for each of the "novel" classes. This paper proposes the idea of associative alignment for leveraging part of the base data by aligning the novel training…

Computer Vision and Pattern Recognition · Computer Science 2020-08-05 Arman Afrasiyabi , Jean-François Lalonde , Christian Gagné

The class-wise training losses often diverge as a result of the various levels of intra-class and inter-class appearance variation, and we find that the diverging class-wise training losses cause the uncalibrated prediction with its…

Machine Learning · Computer Science 2023-06-21 Seungjin Jung , Seungmo Seo , Yonghyun Jeong , Jongwon Choi

Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset. Various methods have been proposed using a one-class-one-model approach, but these…

Machine Learning · Computer Science 2023-12-07 Jae Young Lee , Wonjun Lee , Jaehyun Choi , Yongkwi Lee , Young Seog Yoon

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by…

Machine Learning · Computer Science 2019-06-25 Jun Wen , Nenggan Zheng , Junsong Yuan , Zhefeng Gong , Changyou Chen

Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. However, real-world applications are required to perform on any…

Machine Learning · Computer Science 2023-03-07 Vihari Piratla

Safety alignment for large language models (LLMs) aims to reduce harmful or unsafe behavior while preserving general utility. However, recent findings reveal that alignment effects can be fragile: lightweight post-alignment manipulations,…

Artificial Intelligence · Computer Science 2026-05-29 Zhihao Liu , Yifan Wu , Jian Lou , Di Wang , Yuxi Zhou , Yuke Hu

For machine learning models to be reliable and trustworthy, their decisions must be interpretable. As these models find increasing use in safety-critical applications, it is important that not just the model predictions but also their…

Machine Learning · Computer Science 2023-12-19 Sandesh Kamath , Sankalp Mittal , Amit Deshpande , Vineeth N Balasubramanian

Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the data distribution. For example, in the biomedical field, their performance can be affected by…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Pedro Vianna , Muawiz Chaudhary , Paria Mehrbod , An Tang , Guy Cloutier , Guy Wolf , Michael Eickenberg , Eugene Belilovsky

Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut features, has been observed across domains, including medical…

Machine Learning · Computer Science 2025-09-23 Mihnea Ghitu , Vihari Piratla , Matthew Wicker

Quantification learning deals with the task of estimating the target label distribution under label shift. In this paper, we first present a unifying framework, distribution feature matching (DFM), that recovers as particular instances…

Machine Learning · Statistics 2023-07-04 Bastien Dussap , Gilles Blanchard , Badr-Eddine Chérief-Abdellatif