English
Related papers

Related papers: A Toolkit for Detecting Spurious Correlations in S…

200 papers

Recent years have witnessed the great success of self-supervised learning (SSL) in recommendation systems. However, SSL recommender models are likely to suffer from spurious correlations, leading to poor generalization. To mitigate spurious…

Information Retrieval · Computer Science 2024-04-19 Xinyu Lin , Yiyan Xu , Wenjie Wang , Yang Zhang , Fuli Feng

We consider one of the most basic multiple testing problems that compares expectations of multivariate data among several groups. As a test statistic, a conventional (approximate) $t$-statistic is considered, and we determine its rejection…

Methodology · Statistics 2016-12-20 Yoshiyuki Ninomiya , Satoshi Kuriki , Toshihiko Shiroishi , Toyoyuki Takada

Many applications of speech technology require more and more audio data. Automatic assessment of the quality of the collected recordings is important to ensure they meet the requirements of the related applications. However, effective and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Qiang Huang , Thomas Hain

Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model generalization and robustness. Research in this area, however,…

Machine Learning · Computer Science 2024-12-09 David Steinmann , Felix Divo , Maurice Kraus , Antonia Wüst , Lukas Struppek , Felix Friedrich , Kristian Kersting

Spurious correlations allow flexible models to predict well during training but poorly on related test distributions. Recent work has shown that models that satisfy particular independencies involving correlation-inducing \textit{nuisance}…

Machine Learning · Computer Science 2022-06-10 Mark Goldstein , Jörn-Henrik Jacobsen , Olina Chau , Adriel Saporta , Aahlad Puli , Rajesh Ranganath , Andrew C. Miller

Positive-unlabeled learning (PUL) aims at learning a binary classifier from only positive and unlabeled training data. Even though real-world applications often involve imbalanced datasets where the majority of examples belong to one class,…

Machine Learning · Statistics 2024-03-12 Emilio Dorigatti , Jann Goschenhofer , Benjamin Schubert , Mina Rezaei , Bernd Bischl

We initiate a unified theoretical and algorithmic study of a key problem in weak-to-strong (W2S) generalization: when fine-tuning a strong pre-trained student with pseudolabels from a weaker teacher on a downstream task with spurious…

Machine Learning · Computer Science 2026-03-23 Chenruo Liu , Yijun Dong , Qi Lei

The scalability of the labeling process and the attainable quality of labels have become limiting factors for many applications of machine learning. The programmatic creation of labeled datasets via the synthesis of noisy heuristics…

Machine Learning · Computer Science 2019-12-18 Benedikt Boecking , Artur Dubrawski

Labeled data is a critical resource for training and evaluating machine learning models. However, many real-life datasets are only partially labeled. We propose a semi-supervised machine learning training strategy to improve event detection…

Computer Vision and Pattern Recognition · Computer Science 2022-10-05 Florian Dubost , Erin Hong , Nandita Bhaskhar , Siyi Tang , Daniel Rubin , Christopher Lee-Messer

To capture the relationship between samples and labels, conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Junhyun Nam , Sangwoo Mo , Jaeho Lee , Jinwoo Shin

Large-scale dialogue datasets have recently become available for training neural dialogue agents. However, these datasets have been reported to contain a non-negligible number of unacceptable utterance pairs. In this paper, we propose a…

Computation and Language · Computer Science 2020-10-07 Reina Akama , Sho Yokoi , Jun Suzuki , Kentaro Inui

The Statistical Toolkit is an open source system specialized in the statistical comparison of distributions. It addresses requirements common to different experimental domains, such as simulation validation (e.g. comparison of experimental…

Computational Physics · Physics 2015-06-11 M Batic , A. M. Paganoni , A. Pfeiffer , M. G. Pia , A. Ribon

Neural networks often learn spurious correlations when exposed to biased training data, leading to poor performance on out-of-distribution data. A biased dataset can be divided, according to biased features, into bias-aligned samples (i.e.,…

Machine Learning · Computer Science 2023-08-17 Rui Hu , Yahan Tu , Jitao Sang

Visual tracking is fundamentally the problem of regressing the state of the target in each video frame. While significant progress has been achieved, trackers are still prone to failures and inaccuracies. It is therefore crucial to…

Computer Vision and Pattern Recognition · Computer Science 2020-03-30 Martin Danelljan , Luc Van Gool , Radu Timofte

Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable pronunciations, and unstructured or semi-structured…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-07 Yaman Kumar Singla , Avykat Gupta , Shaurya Bagga , Changyou Chen , Balaji Krishnamurthy , Rajiv Ratn Shah

When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-21 Robert Flynn , Anton Ragni

We investigate whether three types of post hoc model explanations--feature attribution, concept activation, and training point ranking--are effective for detecting a model's reliance on spurious signals in the training data. Specifically,…

Machine Learning · Computer Science 2022-12-12 Julius Adebayo , Michael Muelly , Hal Abelson , Been Kim

Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks. In this work, we aim to answer the following research question: Can we reduce spurious…

Computation and Language · Computer Science 2023-09-19 Zirui He , Huiqi Deng , Haiyan Zhao , Ninghao Liu , Mengnan Du

Natural Language Inference (NLI) evaluation is crucial for assessing language understanding models; however, popular datasets suffer from systematic spurious correlations that artificially inflate actual model performance. To address this,…

Computation and Language · Computer Science 2024-10-07 Adrian Cosma , Stefan Ruseti , Mihai Dascalu , Cornelia Caragea

Automated speech analysis is a thriving approach to detect early markers of Alzheimer's disease (AD). Yet, recording conditions in most AD datasets are heterogeneous, with patients and controls often evaluated in different acoustic…

‹ Prev 1 4 5 6 7 8 10 Next ›