Graph neural networks (GNNs) have become increasingly popular for classification tasks on
graph-structured data. Yet, the interplay between graph topology and feature evolution in …

Neural collapse (NC) refers to the surprising structure of the last layer of deep neural
networks in the terminal phase of gradient descent training. Recently, an increasing amount …

Over the past decade, deep learning has proven to be a highly effective tool for learning
meaningful features from raw data. However, it remains an open question how deep …

This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures
the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC) …

Neural collapse provides an elegant mathematical characterization of learned last layer
representations (aka features) and classifier weights in deep classification models. Such …

Deep Neural Collapse (DNC) refers to the surprisingly rigid structure of the data
representations in the final layers of Deep Neural Networks (DNNs). Though the …

Over the past few years, an extensively studied phenomenon in training deep networks is
the implicit bias of gradient descent towards parsimonious solutions. In this work, we …

Neural collapse ($\mathcal {NC} $) is a phenomenon observed in classification tasks where
top-layer representations collapse into their class means, which become equinorm …

Recent studies empirically demonstrate the positive relationship between the transferability
of neural networks and the in-class variation of the last layer features. The recently …

Label smoothing loss is a widely adopted technique to mitigate overfitting in deep neural
networks. This paper studies label smoothing from the perspective of Neural Collapse (NC) …