R-Mixup: Riemannian Mixup for Biological Networks

by   Xuan Kan, et al.
Emory University
Georgia Institute of Technology

Biological networks are commonly used in biomedical and healthcare domains to effectively model the structure of complex biological systems with interactions linking biological entities. However, due to their characteristics of high dimensionality and low sample size, directly applying deep learning models on biological networks usually faces severe overfitting. In this work, we propose R-MIXUP, a Mixup-based data augmentation technique that suits the symmetric positive definite (SPD) property of adjacency matrices from biological networks with optimized training efficiency. The interpolation process in R-MIXUP leverages the log-Euclidean distance metrics from the Riemannian manifold, effectively addressing the swelling effect and arbitrarily incorrect label issues of vanilla Mixup. We demonstrate the effectiveness of R-MIXUP with five real-world biological network datasets on both regression and classification tasks. Besides, we derive a commonly ignored necessary condition for identifying the SPD matrices of biological networks and empirically study its influence on the model performance. The code implementation can be found in Appendix E.


page 1

page 2

page 3

page 4


Riemannian Metric Learning for Symmetric Positive Definite Matrices

Over the past few years, symmetric positive definite (SPD) matrices have...

Probabilistic Learning Vector Quantization on Manifold of Symmetric Positive Definite Matrices

In this paper, we develop a new classification method for manifold-value...

Data Analysis using Riemannian Geometry and Applications to Chemical Engineering

We explore the use of tools from Riemannian geometry for the analysis of...

Riemannian Multiclass Logistics Regression for SPD Neural Networks

Deep neural networks for learning symmetric positive definite (SPD) matr...

Riemannian batch normalization for SPD neural networks

Covariance matrices have attracted attention for machine learning applic...

Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations

We propose the Onto2Vec method, an approach to learn feature vectors for...

Please sign up or login with your details

Forgot password? Click here to reset