mlsanityData to 7 Oct 2026

R-Mixup: Riemannian Mixup for Biological Networks

arXiv 2306.02532 ↗First posted 5 Jun 2023cs.LG cs.AI q-bio.QMcited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 46 of its 107 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

46 of 107 references.

References · 46

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  6. 2017A Closer Look at Memorization in Deep Networkscited by 936
  7. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  8. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  9. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  10. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
  11. 2020MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classificationcited by 186
  12. 2016A Riemannian Network for SPD Matrix Learningcited by 162
34 more
  1. 2018MixUp as Locally Linear Out-Of-Manifold Regularizationcited by 158
  2. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  3. 2020Remix: Rebalanced Mixupcited by 144
  4. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  5. 2022Brain Network Transformercited by 92
  6. 2022BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networkscited by 73
  7. 2019Riemannian batch normalization for SPD neural networkscited by 72
  8. 2022FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generationcited by 66
  9. 2020SuperMix: Supervising the Mixing Data Augmentationcited by 58
  10. 2022Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysiscited by 58
  11. 2022C-Mixup: Improving Generalization in Regressioncited by 57
  12. 2020SeqMix: Augmenting Active Sequence Labeling via Sequence Mixupcited by 52
  13. 2022MAtt: A Manifold Attention Network for EEG Decodingcited by 43
  14. 2019Graph Neural Network for Interpreting Task-fMRI Biomarkerscited by 40
  15. 2021MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognitioncited by 38
  16. 2021GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Predictioncited by 36
  17. 2020SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarizationcited by 33
  18. 2021AlignMixup: Improving Representations By Interpolating Aligned Featurescited by 33
  19. 2014Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernelscited by 30
  20. 2021Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integrationcited by 21
  21. 2014Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matricescited by 20
  22. 2017Bootstrapping Graph Convolutional Neural Networks for Autism Spectrum Disorder Classificationcited by 20
  23. 2022Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approachcited by 16
  24. 2022Data-Efficient Brain Connectome Analysis via Multi-Task Meta-Learningcited by 15
  25. 2023Neighborhood-Regularized Self-Training for Learning with Few Labelscited by 14
  26. 2022Learning Task-Aware Effective Brain Connectivity for fMRI Analysis with Graph Neural Networkscited by 12
  27. 2022Multi-objective Deep Data Generation with Correlated Property Controlcited by 10
  28. 2023PTGB: Pre-Train Graph Neural Networks for Brain Network Analysiscited by 10
  29. 2013Analyzing complex functional brain networks: fusing statistics and network science to understand the braincited by 8
  30. 2023Transformer-Based Hierarchical Clustering for Brain Network Analysiscited by 8
  31. 2022Deep Representations for Time-varying Brain Datasetscited by 3
  32. 2021A Probabilistic Bayesian Approach to Recover R2^* map and Phase Images for Quantitative Susceptibility Mappingcited by 2
  33. 2022Robust Quantitative Susceptibility Mapping via Approximate Message Passing with Parameter Estimationcited by 1
  34. 2023Domain Generalization Deep Graph Transformationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 1; 2026: 3.

8 papers.

  1. 2023Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Modelscited by 20
  2. 2024RC-Mixup: A Data Augmentation Strategy against Noisy Data for Regression Taskscited by 6
  3. 2023Tailoring Mixup to Data for Calibrationcited by 5
  4. 2024Riemannian Geometry-Based EEG Approaches: A Literature Reviewcited by 3
  5. 2026ODEBrain: Continuous-Time EEG Graph for Modeling Dynamic Brain Networkscited by 3
  6. 2025Curvature Enhanced Data Augmentation for Regressioncited by 1
  7. 2026RepSPD: Enhancing SPD Manifold Representation in EEGs via Dynamic Graphscited by 0
  8. 2026Enhancing Protein Representation Learning via Manifold Restore Mixingcited by 0