Using sliced mutual information to study memorization and generalization in deep neural networks
In this paper, we study the memorization and generalization behaviour of deep neural
networks (DNNs) using sliced mutual information (SMI), which is the average of the mutual …
networks (DNNs) using sliced mutual information (SMI), which is the average of the mutual …
On Neural Networks Fitting, Compression, and Generalization Behavior via Information-Bottleneck-like Approaches
It is well-known that a neural network learning process—along with its connections to fitting,
compression, and generalization—is not yet well understood. In this paper, we propose a …
compression, and generalization—is not yet well understood. In this paper, we propose a …
A lightweight and personalized edge federated learning model
P Yuan, L Shi, X Zhao, J Zhang - Complex & Intelligent Systems, 2024 - Springer
As a new distributed machine learning paradigm, federated learning has gained increasing
attention in the industry and research community. However, federated learning is …
attention in the industry and research community. However, federated learning is …
Pointwise Sliced Mutual Information for Neural Network Explainability
When deploying deep learning models such as convolutional neural networks (CNNs) in
safety-critical domains, it is important to understand the predictions made by these black-box …
safety-critical domains, it is important to understand the predictions made by these black-box …
Gone With the Bits: Benchmarking Bias in Facial Phenotype Degradation Under Low-Rate Neural Compression
In this study, we investigate how facial phenotypes are distorted under neural image
compression and the disparity of this distortion across racial groups. Neural compression …
compression and the disparity of this distortion across racial groups. Neural compression …