Covariance Neural Network

Covariance neural networks (VNNs) are a class of neural networks that leverage the covariance matrix of data as input, enabling the analysis of relationships between variables and offering advantages over traditional methods like principal component analysis (PCA). Current research focuses on improving VNN stability and efficiency through techniques like sparsification and online updates, as well as exploring applications in diverse fields such as brain imaging, time series analysis, and reinforcement learning. The ability of VNNs to handle high-dimensional, correlated data, coupled with their demonstrated stability and transferability across datasets, makes them a significant tool for various scientific and engineering applications.

Papers

November 2, 2024

Covariance-based Space Regularization for Few-shot Class Incremental Learning
Yijie Hu, Guanyu Yang, Zhaorui Tan, Xiaowei Huang, Kaizhu Huang, Qiu-Feng Wang
LeArning Abstract Discriminative Representation Class Distribution Shot Training Covariance Neural Network Spatially Varying Regularization

October 2, 2024

Sparse Covariance Neural Networks
Andrea Cavallo, Zhan Gao, Elvin Isufi
Covariance Estimation Sparse Principal Component Analysis Covariance Neural Network Stable Neural Network

September 16, 2024

Spatiotemporal Covariance Neural Networks
Andrea Cavallo, Mohammad Sabbaqi, Elvin Isufi
Temporal Interaction Covariance Alignment Covariance Neural Network

April 10, 2024

Minimizing Chebyshev Prototype Risk Magically Mitigates the Perils of Overfitting
Nathaniel Dean, Dilip Sarkar
Loss Function Model Overfitting Covariance Neural Network Inter Class Feature

March 23, 2024

Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy Search
Can Bogoclu, Robert Vosshall, Kevin Cremanns, Dirk Roos
Model Based Reinforcement Learning World Model Uncertainty Aware Trajectory Sampling Covariance Neural Network

February 12, 2024

Towards a Foundation Model for Brain Age Prediction using coVariance Neural Networks
Saurabh Sihag, Gonzalo Mateos, Alejandro Ribeiro
Foundation Model Brain Age Covariance Neural Network Cortical Thickness

January 1, 2024

Learn to integrate parts for whole through correlated neural variability
Zhichao Zhu, Yang Qi, Wenlian Lu, Jianfeng Feng
Computational Neuroscience Part Identification Perceptual Information Covariance Neural Network Neural Code Variability Collapse

November 27, 2023

Riemannian Prediction of Anatomical Diagnoses in Congenital Heart Disease based on 12-lead ECGs
Muhammet Alkan, Gruschen Veldtman, Fani Deligianni
Anatomical Structure Riemannian Geometry Lead ECG Riemannian Geometry Approach Covariance Neural Network

July 21, 2023

Tuning Pre-trained Model via Moment Probing
Mingze Gao, Qilong Wang, Zhenyi Lin, Pengfei Zhu, Qinghua Hu, Jingbo Zhou
Pre Trained Model Feature Learning Linear Classifier Hyper Tune Covariance Neural Network Second Order Moment

June 5, 2023

A Deep Learning Approach Utilizing Covariance Matrix Analysis for the ISBI Edited MRS Reconstruction Challenge
Julian P. Merkofer, Dennis M. J. van de Sande, Sina Amirrajab, Gerhard S. Drenthen, Mitko Veta, Jacobus F. A. Jansen, Marcel Breeuwer, Ruud J. G. van Sloun
Machine Learning Model Magnetic Resonance Noisy Input Covariance Neural Network Ex Vivo Magnetic Resonance Spectroscopic Imaging Sample Covariance Matrix

May 27, 2023

Explainable Brain Age Prediction using coVariance Neural Networks
Saurabh Sihag, Gonzalo Mateos, Corey McMillan, Alejandro Ribeiro
Brain Age Anatomical Structure Covariance Neural Network Cortical Thickness

May 2, 2023

Transferability of coVariance Neural Networks and Application to Interpretable Brain Age Prediction using Anatomical Features
Saurabh Sihag, Gonzalo Mateos, Corey T. McMillan, Alejandro Ribeiro
Convolutional Neural Network Application Proficiency Task Transferability Brain Age Anatomical Structure Covariance Conditioning Covariance Neural Network Cortical Thickness

March 21, 2023

Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation
Fulin Liu, Yinlin Hu, Mathieu Salzmann
6D Object 6D Pose Estimation End to End Learning Covariance Neural Network Pose Distribution PnP Algorithm

February 1, 2023

Deterministic equivalent and error universality of deep random features learning
Dominik Schröder, Hugo Cui, Daniil Dmitriev, Bruno Loureiro
Covariance Neural Network Gaussian Universality Deep Random Feature

November 28, 2022

Metric Learning as a Service with Covariance Embedding
Imam Mustafa Kamal, Hyerim Bae, Ling Liu
Metric Learning Service Provider Covariance Conditioning Class Similarity Covariance Neural Network

October 28, 2022

Predicting Brain Age using Transferable coVariance Neural Networks
Saurabh Sihag, Gonzalo Mateos, Corey McMillan, Alejandro Ribeiro
Brain Age Covariance Conditioning Brain Aging Covariance Neural Network Cortical Thickness

June 21, 2022

TiCo: Transformation Invariance and Covariance Contrast for Self-Supervised Visual Representation Learning
Jiachen Zhu, Rafael M. Moraes, Serkan Karakulak, Vlad Sobol, Alfredo Canziani, Yann LeCun
Invariant Representation Self Supervised Visual Representation Covariance Conditioning Covariance Neural Network Transformation Invariance

May 31, 2022

coVariance Neural Networks
Saurabh Sihag, Gonzalo Mateos, Corey McMillan, Alejandro Ribeiro
Graph Neural Network Principal Component Analysis Covariance Matrix Principal Component Covariance Neural Network

December 8, 2021

NICE-Beam: Neural Integrated Covariance Estimators for Time-Varying Beamformers
Jonah Casebeer, Jacob Donley, Daniel Wong, Buye Xu, Anurag Kumar
Speech Enhancement Adaptive Beamforming Covariance Neural Network