Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA
Preprint
Abstract
Particle-based Bayesian deep learning often requires a similarity metric to compare two networks. However, naive similarity metrics lack permutation invariance and are inappropriate for comparing networks. Centered Kernel Alignment (CKA) on feature kernels has been proposed to compare deep networks but has not been used as an optimization objective in Bayesian deep learning. In this paper, we explore the use of CKA in Bayesian deep learning to generate diverse ensembles and hypernetworks that output a network posterior. Noting that CKA projects kernels onto a unit hypersphere and that directly optimizing the CKA objective leads to diminishing gradients when two networks are very similar. We propose adopting the approach of hyperspherical energy (HE) on top of CKA kernels to address this drawback and improve training stability. Additionally, by leveraging CKA-based feature kernels, we derive feature repulsive terms applied to synthetically generated outlier examples. Experiments on both diverse ensembles and hypernetworks show that our approach significantly outperforms baselines in terms of uncertainty quantification in both synthetic and realistic outlier detection tasks.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- A survey of uncertainty in deep neural networksArtificial Intelligence Review, 2023
- Hypernetwork-Based Adaptive Image Restoration2023
- Geometry in sampling methods: A review on manifold MCMC and particle-based variational inference methods2022
- HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing2022
- On the Decreasing Power of Kernel and Distance Based Nonparametric Hypothesis Tests in High DimensionsProceedings of the AAAI Conference on Artificial Intelligence, 2015
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- The use of the area under the ROC curve in the evaluation of machine learning algorithmsPattern Recognition, 1997