English
Related papers

Related papers: Data-SUITE: Data-centric identification of in-dist…

200 papers

In distributed and federated learning, heterogeneity across data sources remains a major obstacle to effective model aggregation and convergence. We focus on feature heterogeneity and introduce energy distance as a sensitive measure for…

Machine Learning · Statistics 2025-01-28 Mengchen Fan , Baocheng Geng , Roman Shterenberg , Joseph A. Casey , Zhong Chen , Keren Li

In modern federated learning, one of the main challenges is to account for inherent heterogeneity and the diverse nature of data distributions for different clients. This problem is often addressed by introducing personalization of the…

Machine Learning · Statistics 2023-12-19 Nikita Kotelevskii , Samuel Horváth , Karthik Nandakumar , Martin Takáč , Maxim Panov

We address the goal of conducting inference about a smooth finite-dimensional parameter by utilizing individual-level data from various independent sources. Recent advancements have led to the development of a comprehensive theory capable…

Statistics Theory · Mathematics 2025-11-19 Ellen Graham , Marco Carone , Andrea Rotnitzky

Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs during deployment. However, current state-of-the-art approaches…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Vasu Singla , Pedro Sandoval-Segura , Micah Goldblum , Jonas Geiping , Tom Goldstein

Many machine learning models appear to deploy effortlessly under distribution shift, and perform well on a target distribution that is considerably different from the training distribution. Yet, learning theory of distribution shift bounds…

Machine Learning · Computer Science 2024-05-30 Robi Bhattacharjee , Nick Rittler , Kamalika Chaudhuri

As diffusion models become increasingly popular, the misuse of copyrighted and private images has emerged as a major concern. One promising solution to mitigate this issue is identifying the contribution of specific training samples in…

Machine Learning · Computer Science 2025-03-24 Jinxu Lin , Linwei Tao , Minjing Dong , Chang Xu

The reliability and proper function of data-driven applications hinge on the data's continued conformance to the applications' initial design. When data deviates from this initial profile, system behavior becomes unpredictable. Data…

Databases · Computer Science 2021-01-05 Anna Fariha , Ashish Tiwari , Arjun Radhakrishna , Sumit Gulwani , Alexandra Meliou

Domain adaptation (DA) aims to generalize a learning model across training and testing data despite the mismatch of their data distributions. In light of a theoretical estimation of upper error bound, we argue in this paper that an…

Computer Vision and Pattern Recognition · Computer Science 2018-01-01 Lingkun Luo , Liming Chen , Shiqiang Hu , Ying Lu , Xiaofang Wang

Data imbalance is a well-known issue in the field of machine learning, attributable to the cost of data collection, the difficulty of labeling, and the geographical distribution of the data. In computer vision, bias in data distribution…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Shubham Shrivastava , Xianling Zhang , Sushruth Nagesh , Armin Parchami

Causal inference across multiple data sources offers a promising avenue to enhance the generalizability and replicability of scientific findings. However, data integration methods for time-to-event outcomes, common in biomedical research,…

Methodology · Statistics 2025-05-16 Yi Liu , Alexander W. Levis , Ke Zhu , Shu Yang , Peter B. Gilbert , Larry Han

In this work, we propose CODE, an extension of existing work from the field of explainable AI that identifies class-specific recurring patterns to build a robust Out-of-Distribution (OoD) detection method for visual classifiers. CODE does…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Romain Xu-Darme , Julien Girard-Satabin , Darryl Hond , Gabriele Incorvaia , Zakaria Chihani

Person re-identification (Re-ID) models usually show a limited performance when they are trained on one dataset and tested on another dataset due to the inter-dataset bias (e.g. completely different identities and backgrounds) and the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-29 Jiajie Tian , Zhu Teng , Rui Li , Yan Li , Baopeng Zhang , Jianping Fan

Calibrated uncertainty estimates in machine learning are crucial to many fields such as autonomous vehicles, medicine, and weather and climate forecasting. While there is extensive literature on uncertainty calibration for classification,…

Machine Learning · Computer Science 2021-03-16 Eric Zelikman , Christopher Healy , Sharon Zhou , Anand Avati

Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Sanghun Jung , Jungsoo Lee , Nanhee Kim , Amirreza Shaban , Byron Boots , Jaegul Choo

Objective-The main purpose of this paper is to construct a distributed clustering algorithm such that each distributed cluster can perform the data accuracy at their respective cluster head node before data aggregation and transmit the data…

Networking and Internet Architecture · Computer Science 2011-01-12 Jyotirmoy Karjee , H. S Jamadagni

Detectors trained with massive labeled data often exhibit dramatic performance degradation in some particular scenarios with data distribution gap. To alleviate this problem of domain shift, conventional wisdom typically concentrates solely…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Liang Zhao , Limin Wang

In this paper we present a heuristic method to provide individual explanations for those elements in a dataset (data points) which are wrongly predicted by a given classifier. Since the general case is too difficult, in the present work we…

Machine Learning · Computer Science 2023-02-21 Sheng Zhou , Pierre Blanchart , Michel Crucianu , Marin Ferecatu

In machine learning, we traditionally evaluate the performance of a single model, averaged over a collection of test inputs. In this work, we propose a new approach: we measure the performance of a collection of models when evaluated on a…

Machine Learning · Computer Science 2022-06-08 Gal Kaplun , Nikhil Ghosh , Saurabh Garg , Boaz Barak , Preetum Nakkiran

Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce uncalibrated closed-set predictions for OOD data. A more…

Existing works show that although modern neural networks achieve remarkable generalization performance on the in-distribution (ID) dataset, the accuracy drops significantly on the out-of-distribution (OOD) datasets \cite{recht2018cifar,…

Machine Learning · Computer Science 2022-03-30 Berfin Simsek , Melissa Hall , Levent Sagun