English
Related papers

Related papers: Diagnosing Generalization Failures from Representa…

200 papers

Poor generalization is one symptom of models that learn to predict target variables using spuriously-correlated image features present only in the training distribution instead of the true image features that denote a class. It is often…

Computer Vision and Pattern Recognition · Computer Science 2021-02-11 Joseph D. Viviano , Becks Simpson , Francis Dutil , Yoshua Bengio , Joseph Paul Cohen

Large language models (LLMs) have achieved remarkable proficiency on solving diverse problems. However, their generalization ability is not always satisfying and the generalization problem is common for generative transformer models in…

Machine Learning · Computer Science 2024-08-20 Xingcheng Xu , Zihao Pan , Haipeng Zhang , Yanqing Yang

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind…

Machine Learning · Computer Science 2014-04-24 Yoshua Bengio , Aaron Courville , Pascal Vincent

The problem of identifying geometric structure in data is a cornerstone of (unsupervised) learning. As a result, Geometric Representation Learning has been widely applied across scientific and engineering domains. In this work, we…

Machine Learning · Computer Science 2025-06-03 Imran Nasim , Melanie Weber

Despite significant advances in the field of deep learning in applications to various fields, explaining the inner processes of deep learning models remains an important and open question. The purpose of this article is to describe and…

Machine Learning · Computer Science 2022-04-20 German Magai , Anton Ayzenberg

The ability to generalize out-of-domain (OOD) is an important goal for deep neural network development, and researchers have proposed many high-performing OOD generalization methods from various foundations. While many OOD algorithms…

Machine Learning · Computer Science 2022-08-29 Zining Zhu , Soroosh Shahtalebi , Frank Rudzicz

Constructing transferable descriptors for conformation representation of molecular and biological systems finds numerous applications in drug discovery, learning-based molecular dynamics, and protein mechanism analysis. Geometric graph…

Machine Learning · Computer Science 2024-10-30 Zihan Pengmei , Zhengyuan Shen , Zichen Wang , Marcus Collins , Huzefa Rangwala

Traditional machine learning methods heavily rely on the independent and identically distribution assumption, which imposes limitations when the test distribution deviates from the training distribution. To address this crucial issue,…

Machine Learning · Computer Science 2024-03-26 Qin Tian , Wenjun Wang , Chen Zhao , Minglai Shao , Wang Zhang , Dong Li

The underspecification of most machine learning pipelines means that we cannot rely solely on validation performance to assess the robustness of deep learning systems to naturally occurring distribution shifts. Instead, making sure that a…

Modern machine learning increasingly leverages the insight that high-dimensional data often lie near low-dimensional, non-linear manifolds, an idea known as the manifold hypothesis. By explicitly modeling the geometric structure of data…

Machine Learning · Computer Science 2026-03-02 Willem Diepeveen , Deanna Needell

While modern deep neural architectures generalise well when test data is sampled from the same distribution as training data, they fail badly for cases when the test data distribution differs from the training distribution even along a few…

Machine Learning · Computer Science 2020-10-06 Duo Wang , Mateja Jamnik , Pietro Lio

The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in safety-critical applications. Most existing methods either…

Machine Learning · Computer Science 2021-02-25 Leo Schwinn , An Nguyen , René Raab , Leon Bungert , Daniel Tenbrinck , Dario Zanca , Martin Burger , Bjoern Eskofier

Deep learning-based online mapping has emerged as a cornerstone of autonomous driving, yet these models frequently fail to generalize beyond familiar environments. We propose a framework to identify and measure the underlying failure modes…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Michael Hubbertz , Qi Han , Tobias Meisen

Graph Neural Networks (GNNs) have become the standard method for learning from networks across fields ranging from biology to social systems, yet a principled understanding of what enables them to extract meaningful representations, or why…

Machine Learning · Statistics 2026-03-19 Nil Ayday , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar

Neural multivariate regression underpins a wide range of domains, including control, robotics, and finance, yet the geometry of its learned representations remains poorly characterized. While neural collapse has been shown to benefit…

Machine Learning · Computer Science 2026-05-11 George Andriopoulos , Zixuan Dong , Bimarsha Adhikari , Keith Ross

In this paper, we study the generalization capabilities of geometric graph neural networks (GNNs). We consider GNNs over a geometric graph constructed from a finite set of randomly sampled points over an embedded manifold with topological…

Signal Processing · Electrical Eng. & Systems 2025-06-10 Zhiyang Wang , Juan Cervino , Alejandro Ribeiro

This paper presents a novel evaluation framework for Out-of-Distribution (OOD) detection that aims to assess the performance of machine learning models in more realistic settings. We observed that the real-world requirements for testing OOD…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Vahid Reza Khazaie , Anthony Wong , Mohammad Sabokrou

Traditional evaluation metrics for learned models that report aggregate scores over a test set are insufficient for surfacing important and informative patterns of failure over features and instances. We introduce and study a method aimed…

Computer Vision and Pattern Recognition · Computer Science 2021-06-15 Sahil Singla , Besmira Nushi , Shital Shah , Ece Kamar , Eric Horvitz

A common assumption in representation learning is that globally well-distributed embeddings support robust and generalizable representations. This focus has shaped both training objectives and evaluation protocols, implicitly treating…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Jiwan Chung , Seon Joo Kim

Generalization remains a central yet unresolved challenge in deep learning, particularly the ability to predict a model's performance beyond its training distribution using quantities available prior to test-time evaluation. Building on the…