English
Related papers

Related papers: Neural Collapse for Cross-entropy Class-Imbalanced…

200 papers

Training of deep neural networks heavily depends on the data distribution. In particular, the networks easily suffer from class imbalance. The trained networks would recognize the frequent classes better than the infrequent classes. To…

Computer Vision and Pattern Recognition · Computer Science 2020-03-12 Byungju Kim , Junmo Kim

Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets. However, imbalanced class distributions still limit the wide applicability of these models due to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-05 Yechan Kim , Younkwan Lee , Moongu Jeon

Graph Neural Network (GNN) is an emerging technique for graph-based learning tasks such as node classification. In this work, we reveal the vulnerability of GNN to the imbalance of node labels. Traditional solutions for imbalanced…

Machine Learning · Computer Science 2022-02-08 Xiaohe Li , Lijie Wen , Yawen Deng , Fuli Feng , Xuming Hu , Lei Wang , Zide Fan

Today, deep neural networks are widely used since they can handle a variety of complex tasks. Their generality makes them very powerful tools in modern technology. However, deep neural networks are often overparameterized. The usage of…

Machine Learning · Computer Science 2024-12-20 Zhu Liao , Nour Hezbri , Victor Quétu , Van-Tam Nguyen , Enzo Tartaglione

Neural networks can be trained to solve regression problems by using gradient-based methods to minimize the square loss. However, practitioners often prefer to reformulate regression as a classification problem, observing that training on…

Machine Learning · Computer Science 2023-03-02 Lawrence Stewart , Francis Bach , Quentin Berthet , Jean-Philippe Vert

Transferability estimation aims to provide heuristics for quantifying how suitable a pre-trained model is for a specific downstream task, without fine-tuning them all. Prior studies have revealed that well-trained models exhibit the…

Machine Learning · Computer Science 2023-10-10 Yuhe Ding , Bo Jiang , Lijun Sheng , Aihua Zheng , Jian Liang

This paper investigates the deep learning optimization problem with softmax cross-entropy loss. We propose a layer separation strategy to alleviate the strong nonconvexity encountered during training deep networks. For cross-entropy models…

Machine Learning · Computer Science 2026-04-28 Yaru Liu , Michael K. Ng , Yiqi Gu

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

We study the optimization of wide neural networks (NNs) via gradient flow (GF) in setups that allow feature learning while admitting non-asymptotic global convergence guarantees. First, for wide shallow NNs under the mean-field scaling and…

Machine Learning · Computer Science 2022-04-25 Zhengdao Chen , Eric Vanden-Eijnden , Joan Bruna

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Artificial Intelligence · Computer Science 2026-01-06 Josef Ott

The loss function is a key component in deep learning models. A commonly used loss function for classification is the cross entropy loss, which is a simple yet effective application of information theory for classification problems. Based…

Computer Vision and Pattern Recognition · Computer Science 2020-10-13 Zeyu Song , Dongliang Chang , Zhanyu Ma , Xiaoxu Li , Zheng-Hua Tan

This work investigates the phenomenon of Neural Collapse (NC) in multi-label classification, extending its conceptual framework from multi-class learning to general correlated and imbalanced multi-label settings. Although recent studies…

Machine Learning · Computer Science 2026-05-05 Xiaoxuan Ma , Yixuan Yang , Song Li , Xiangyun Hui

A major challenge in Fine-Grained Visual Classification (FGVC) is distinguishing various categories with high inter-class similarity by learning the feature that differentiate the details. Conventional cross entropy trained Convolutional…

Machine Learning · Computer Science 2021-03-17 Runkai Zheng , Zhijia Yu , Yinqi Zhang , Chris Ding , Hei Victor Cheng , Li Liu

Continual Learning enables models to learn and adapt to new tasks while retaining prior knowledge. Introducing new tasks, however, can naturally lead to feature entanglement across tasks, limiting the model's capability to distinguish…

Machine Learning · Computer Science 2025-01-14 Zhongyi Zhou , Yaxin Peng , Pin Yi , Minjie Zhu , Chaomin Shen

A deep convolutional neural network (CNN) has been widely used in image classification and gives better classification accuracy than the other techniques. The softmax cross-entropy loss function is often used for classification tasks. There…

Computer Vision and Pattern Recognition · Computer Science 2020-04-20 Motoshi Abe , Junichi Miyao , Takio Kurita

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, neural collapse, where embeddings converge into a…

Machine Learning · Computer Science 2024-10-08 Huanran Li , Manh Nguyen , Daniel Pimentel-Alarcón

Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a \emph{trade-off}. However, in this paper, we show that for an ensemble of deep learning based…

Machine Learning · Computer Science 2023-10-16 Lin Chen , Michal Lukasik , Wittawat Jitkrittum , Chong You , Sanjiv Kumar

This paper presents a neural network filter method based on contraction operators to address model collapse in recursive training of generative models. Unlike \cite{xu2024probabilistic}, which requires superlinear sample growth…

Machine Learning · Computer Science 2025-12-02 Zongjian Han , Yiran Liang , Ruiwen Wang , Yiwei Luo , Yilin Huang , Xiaotong Song , Dongqing Wei

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

Supervised contrastive loss (SCL) is a competitive and often superior alternative to the cross-entropy loss for classification. While prior studies have demonstrated that both losses yield symmetric training representations under balanced…

Machine Learning · Computer Science 2023-10-20 Ganesh Ramachandra Kini , Vala Vakilian , Tina Behnia , Jaidev Gill , Christos Thrampoulidis
‹ Prev 1 4 5 6 7 8 10 Next ›