Publications

You can also find my articles on Google Scholar.

Publications

Methods

Graph Neural Networks and Representation Learning

• Sowon Jeong, C Donnat.
  LOBSTUR: A Local Bootstrap Framework for Tuning Unsupervised Representations in Graph Neural Networks.
  » Bootstrap-based approach for unsupervised GNN tuning. (Under review at NeurIPS, 2025)

• Juntong Chen, Johannes Schmidt-Hieber, C Donnat, Olga Klopp.
  Understanding the Effect of GCN Convolutions in Regression Tasks.
  AISTATS 2025.
  » Theoretical and empirical analysis of convolutional layers in GCN regression.

• Jihee You, So Won Jeong, C Donnat. Gnumap: A parameter-free approach to unsupervised dimensionality reduction via graph neural networks.

• Sowon Jeong, C Donnat.
  Studying the Effect of GNN Spatial Convolutions on the Embedding Space’s Geometry.
  UAI 2023.
  » Examines how spatial convolutions affect embedding geometry.

• Ilgee Hong, Huy Tran, C Donnat.
  A Simplified Framework for Contrastive Learning for Node Representations.
  Asilomar Conference, 2023.
  » Simplifies and improves contrastive learning for graph nodes.

• C Donnat, M Zitnik, D Hallac, J Leskovec.
  Learning Structural Node Embeddings via Diffusion Wavelets.
  KDD 2018.
  » Embedding method using diffusion wavelets.

Structured Estimation and High-Dimensional Inference

Canonical Correlation Analysis:

• Zixuan Wu, Elena Tuzhilina, C Donnat.
  Efficient Canonical Correlation Analysis with Sparsity.
  » Computationally efficient sparse CCA method. (Under review at JASA, 2025)

• C Donnat, Elena Tuzhilina.
  Canonical Correlation Analysis as Reduced Rank Regression for High-Dimensional Data.
  » Shows equivalence between CCA and reduced rank regression. (Under review at JMLR, 2024)

• Huy Tran, Yating Liu, C Donnat.
  Sparse Topic Modeling via Spectral Decomposition and Thresholding.
  » Topic modeling using spectral decomposition. (Under review at IEEE Signal Processing, 2023)

Topic Modeling:

• Yating Liu, C Donnat.
  Tensor Topic Modeling via HOSVD.
  » Tensor-based topic modeling method. (Under review at JMLR, 2024)

• Yeo Jin Jung, C Donnat.
  Graph-Structured Topic Modeling for Documents with Spatial or Covariate Dependencies.
  » Topic modeling with spatial/covariate structure. (Under review at JASA, 2024)

Network-based inference:

• C Donnat, Olga Klopp, Nicolas Verzelen.
  One-Bit Total Variation Denoising over Networks with Applications to Partially Observed Epidemics.
  » Network-based denoising for binary epidemic data. (Under review at CADS, 2024)

• Huy Tran, Sansen Wei, and C Donnat. Huy, The Generalized Elastic Net for least squares regression with network-aligned signal and correlated design. » Generalized elastic net with total variation penalty on the coefficients. (Under review at IEEE SIPN)

• C Donnat, Susan Holmes. A Constrained Bayesian ICA model for connectome inference. arXiv preprint, 2019.

Statistical Models and Methods for Graph and Network Data

• C Donnat, Susan Holmes.
  Tracking Network Dynamics: A Survey of Distances and Similarity Metrics.
  Annals of Applied Statistics, 2018.
  » Review of network distance metrics.

• C Donnat, Susan Holmes.
  Hierarchical Convex Clustering for Graph Data.
  Asilomar Conference, 2019.
  » Convex hierarchical clustering for graphs.

• N Miolane, J Mathe, C Donnat, et al.
  Geomstats: A Python Package for Riemannian Geometry in Machine Learning.
  JMLR, 2020.
  » Open-source library for geometric statistics and ML.

Applications

Biological and Biomedical Applications

• RP Ferreira, R Ding, F Zhang, H Pu, C Donnat, Y Chen, J Chen.
  Expediting Field-Effect Transistor Chemical Sensor Design with Neuromorphic Spiking Graph Neural Networks.
  Molecular Systems Design & Engineering, 2025.
  » Uses spiking GNNs for chemical sensor development.

• C Donnat, A Levy, F Poitevin, N Miolane.
  Deep Generative Modeling for Volume Reconstruction in Cryo-Electron Microscopy.
  Journal of Structural Biology, 2022.
  » Generative modeling for protein structure reconstruction.

Epidemiology and Public Health

• Saskia Comess, Susan Holmes, C Donnat.
  Statistical Modeling for Practical Pooled Testing during the COVID-19 Pandemic.
  Statistical Science, 2021.
  » Statistical frameworks for efficient pooled testing.

• C Donnat, F Bunbury, M Harris, et al.
  Predicting COVID-19 Transmission to Inform the Management of Mass Events: Model-Based Approach.
  JMIR Public Health Surveill, 2021.
  » Risk modeling for large events.

• C Donnat, N. Miolane, J. Kreindler and F. Bunbury. Bayesian Hierarchical Network for Combining Heterogeneous Data Sources in Medical Diagnoses.
  Machine Learning for Health. PMLR, 2020.

• C Donnat, Susan Holmes.
  Modeling the Heterogeneity in COVID-19’s Reproductive Number and Its Impact on Predictive Scenarios.
  Journal of Applied Statistics, 2021.
  » Analyzes variability in disease transmission.

Neuroscience

• Nature Collaboration (incl. C Donnat).
  Variability in the Analysis of a Single Neuroimaging Dataset by Many Teams.
  Nature, 2020.
  » Large-scale reproducibility study in neuroimaging.

Other Applications

• C You, C Donnat, DP Robinson, R Vidal.
  A Divide-and-Conquer Framework for Large-Scale Subspace Clustering.
  Asilomar Conference, 2016.
  » Scalable subspace clustering method.