paper-with-me

홈 › Papers

Feature Collapse

2023-05-25 · Thomas Laurent, James H. von Brecht, Xavier Bresson

We formalize and study a phenomenon called feature collapse that makes precise the intuitive idea that entities playing a similar role in a learning task receive similar representations. As feature collapse requires a notion of task, we leverage a simple but prototypical NLP task to study it. We start by showing experimentally that feature collapse goes hand in hand with generalization. We then prove that, in the large sample limit, distinct words that play identical roles in this NLP task receive identical local feature representations in a neural network. This analysis reveals the crucial role that normalization mechanisms, such as LayerNorm, play in feature collapse and in generalization.

📄 PDF Abstract BibTeX arXiv:2305.16162

Code (1)

xbresson/feature_collapse 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Countering Multi-modal Representation Collapse through Rank-targeted Fusion

2025-11-09 · Seulgi Kim, Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib arxiv

Multi-modal fusion methods often suffer from two types of representation collapse: feature collapse where individual dimensions lose their discriminative power (as measured by eigenspectra), and modality collapse where o…

Action Anticipation

Neural collapse with unconstrained features

2020-11-23 · Dustin G. Mixon, Hans Parshall, Jianzong Pi

Neural collapse is an emergent phenomenon in deep learning that was recently discovered by Papyan, Han and Donoho. We propose a simple "unconstrained features model" in which neural collapse also emerges empirically. By …

Generalized Neural Collapse for a Large Number of Classes

2023-10-09 · Jiachen Jiang, Jinxin Zhou, Peng Wang, Qing Qu 외

Neural collapse provides an elegant mathematical characterization of learned last layer representations (a.k.a. features) and classifier weights in deep classification models. Such results not only provide insights but a…

Face RecognitionRetrieval

Asymptotic Midpoint Mixup for Margin Balancing and Moderate Broadening

2024-01-26 · Hoyong Kim, Semi Lee, Kangil Kim

In the feature space, the collapse between features invokes critical problems in representation learning by remaining the features undistinguished. Interpolation-based augmentation methods such as mixup have shown their …

Representation LearningTransfer Learning

Perturbation Analysis of Neural Collapse

2022-10-29 · Tom Tirer, Haoxiang Huang, Jonathan Niles-Weed

Training deep neural networks for classification often includes minimizing the training loss beyond the zero training error point. In this phase of training, a "neural collapse" behavior has been observed: the variabilit…