English
Related papers

Related papers: Feature contamination: Neural networks learn uncor…

200 papers

Graphs are a fundamental data structure for representing relational information in domains such as social networks, molecular systems, and knowledge graphs. However, graph learning models often suffer from limited generalization when…

Machine Learning · Computer Science 2026-01-30 Haoyang Li , Haibo Chen , Xin Wang , Wenwu Zhu

Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data. The issue can be mitigated by using unlabeled data from the target domain at training time, but because data…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Thomas Duboudin , Emmanuel Dellandréa , Corentin Abgrall , Gilles Hénaff , Liming Chen

To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottleneck. Out-of-distribution samples drawn from distributions…

Machine Learning · Computer Science 2023-08-29 Zhilin Zhao , Longbing Cao

We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the various layers (deep features) with parametric probability…

Machine Learning · Statistics 2019-09-27 Nilesh A. Ahuja , Ibrahima Ndiour , Trushant Kalyanpur , Omesh Tickoo

Domain generalization is the problem of machine learning when the training data and the test data come from different data domains. We present a simple theoretical model of learning to generalize across domains in which there is a…

Machine Learning · Computer Science 2020-02-14 Vikas K. Garg , Adam Kalai , Katrina Ligett , Zhiwei Steven Wu

Although deep neural networks can achieve human-level performance on many object recognition benchmarks, prior work suggests that these same models fail to learn simple abstract relations, such as determining whether two objects are the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Alexa R. Tartaglini , Sheridan Feucht , Michael A. Lepori , Wai Keen Vong , Charles Lovering , Brenden M. Lake , Ellie Pavlick

This paper challenges the prevailing view that convolutional neural network (CNN) filters become increasingly specialized in deeper layers. Motivated by recent observations of clusterable repeating patterns in depthwise separable CNNs…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Zahra Babaiee , Peyman M. Kiasari , Daniela Rus , Radu Grosu

Object recognition and viewpoint estimation lie at the heart of visual understanding. Recent works suggest that convolutional neural networks (CNNs) fail to generalize to out-of-distribution (OOD) category-viewpoint combinations, ie.…

Computer Vision and Pattern Recognition · Computer Science 2021-11-18 Spandan Madan , Timothy Henry , Jamell Dozier , Helen Ho , Nishchal Bhandari , Tomotake Sasaki , Frédo Durand , Hanspeter Pfister , Xavier Boix

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…

Machine Learning · Computer Science 2024-06-10 Liam Collins , Hamed Hassani , Mahdi Soltanolkotabi , Aryan Mokhtari , Sanjay Shakkottai

Deep neural networks are often trained in the over-parametrized regime (i.e. with far more parameters than training examples), and understanding why the training converges to solutions that generalize remains an open problem. Several…

Machine Learning · Statistics 2018-03-23 Hartmut Maennel , Olivier Bousquet , Sylvain Gelly

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high…

Machine Learning · Statistics 2020-11-09 Ben Adlam , Jeffrey Pennington

A major challenge in understanding the generalization of deep learning is to explain why (stochastic) gradient descent can exploit the network architecture to find solutions that have good generalization performance when using high capacity…

Machine Learning · Computer Science 2019-02-12 Yifan Wu , Barnabas Poczos , Aarti Singh

Motivated by the recent empirical successes of deep generative models, we study the computational complexity of the following unsupervised learning problem. For an unknown neural network $F:\mathbb{R}^d\to\mathbb{R}^{d'}$, let $D$ be the…

Machine Learning · Computer Science 2022-06-01 Sitan Chen , Jerry Li , Yuanzhi Li

We study the training and generalization of deep neural networks (DNNs) in the over-parameterized regime, where the network width (i.e., number of hidden nodes per layer) is much larger than the number of training data points. We show that,…

Machine Learning · Computer Science 2019-11-13 Yuan Cao , Quanquan Gu

Implicit neural networks have become increasingly attractive in the machine learning community since they can achieve competitive performance but use much less computational resources. Recently, a line of theoretical works established the…

Machine Learning · Computer Science 2022-10-03 Tianxiang Gao , Hongyang Gao

Deep neural networks for image classification only learn to map in-distribution inputs to their corresponding ground truth labels in training without differentiating out-of-distribution samples from in-distribution ones. This results from…

Machine Learning · Computer Science 2023-08-29 Zhilin Zhao , Longbing Cao , Kun-Yu Lin

Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a network must…

Machine Learning · Statistics 2018-02-15 Terrance DeVries , Graham W. Taylor

Approaches based on deep neural networks have achieved striking performance when testing data and training data share similar distribution, but can significantly fail otherwise. Therefore, eliminating the impact of distribution shifts…

Machine Learning · Computer Science 2021-04-19 Xingxuan Zhang , Peng Cui , Renzhe Xu , Linjun Zhou , Yue He , Zheyan Shen

Graph Neural Networks (GNNs)-based recommendation algorithms typically assume that training and testing data are drawn from independent and identically distributed (IID) spaces. However, this assumption often fails in the presence of…

Machine Learning · Computer Science 2025-04-03 Chu Zhao , Enneng Yang , Yuliang Liang , Pengxiang Lan , Yuting Liu , Jianzhe Zhao , Guibing Guo , Xingwei Wang

In the era of transfer learning, training neural networks from scratch is becoming obsolete. Transfer learning leverages prior knowledge for new tasks, conserving computational resources. While its advantages are well-documented, we uncover…

Machine Learning · Computer Science 2023-11-17 Wojciech Masarczyk , Tomasz Trzciński , Mateusz Ostaszewski
‹ Prev 1 3 4 5 6 7 10 Next ›