Publications (21)
Deep Optimal Transport for Domain Adaptation on SPD Manifolds
Ce Ju, Cuntai Guan
Recent progress in geometric deep learning has drawn increasing attention from the machine learning community toward domain adaptation on symmetric positive definite (SPD) manifold…
Score-Based Data Generation for EEG Spatial Covariance Matrices: Towards Boosting BCI Performance
Ce Ju, Reinmar Josef Kobler, Cuntai Guan
The efficacy of Electroencephalogram (EEG) classifiers can be augmented by increasing the quantity of available data. In the case of geometric deep learning classifiers, the input…
Interaction-aware Kalman Neural Networks for Trajectory Prediction
Ce Ju, Zheng Wang, Cheng Long +2
Forecasting the motion of surrounding obstacles (vehicles, bicycles, pedestrians and etc.) benefits the on-road motion planning for intelligent and autonomous vehicles. Complex sce…
Privacy-Preserving Technology to Help Millions of People: Federated Prediction Model for Stroke Prevention
Ce Ju, Ruihui Zhao, Jichao Sun +11
Prevention of stroke with its associated risk factors has been one of the public health priorities worldwide. Emerging artificial intelligence technology is being increasingly adop…
Survey: Geometric Foundations of Data Reduction
Ce Ju
This survey is written in summer, 2016. The purpose of this survey is to briefly introduce nonlinear dimensionality reduction (NLDR) in data reduction. The first two NLDR were resp…
Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks
Lixin Fan, Kam Woh Ng, Ce Ju +4
This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks. First, we propose to quantitatively measure the…
Representation Learning for Spatial Graphs
Zheng Wang, Ce Ju, Gao Cong +1
Recently, the topic of graph representation learning has received plenty of attention. Existing approaches usually focus on structural properties only and thus they are not suffici…
Stochastic Inverse Reinforcement Learning
Ce Ju
The goal of the inverse reinforcement learning (IRL) problem is to recover the reward functions from expert demonstrations. However, the IRL problem like any ill-posed inverse prob…
Ternary Hashing
Chang Liu, Lixin Fan, Kam Woh Ng +5
This paper proposes a novel ternary hash encoding for learning to hash methods, which provides a principled more efficient coding scheme with performances better than those of the…
Rethinking Uncertainty in Deep Learning: Whether and How it Improves Robustness
Yilun Jin, Lixin Fan, Kam Woh Ng +2
Deep neural networks (DNNs) are known to be prone to adversarial attacks, for which many remedies are proposed. While adversarial training (AT) is regarded as the most robust defen…
Federated Transfer Learning for EEG Signal Classification
Ce Ju, Dashan Gao, Ravikiran Mane +3
The success of deep learning (DL) methods in the Brain-Computer Interfaces (BCI) field for classification of electroencephalographic (EEG) recordings has been restricted by the lac…
Privacy Threats Against Federated Matrix Factorization
Dashan Gao, Ben Tan, Ce Ju +2
Matrix Factorization has been very successful in practical recommendation applications and e-commerce. Due to data shortage and stringent regulations, it can be hard to collect suf…
SPD Learn: A Geometric Deep Learning Python Library for Neural Decoding Through Trivialization
Bruno Aristimunha, Ce Ju, Antoine Collas +5
Implementations of symmetric positive definite (SPD) matrix-based neural networks for neural decoding remain fragmented across research codebases and Python packages. Existing impl…
Tensor-CSPNet: A Novel Geometric Deep Learning Framework for Motor Imagery Classification
Ce Ju, Cuntai Guan
Deep learning (DL) has been widely investigated in a vast majority of applications in electroencephalography (EEG)-based brain-computer interfaces (BCIs), especially for motor imag…
Sheaf Neural Networks on SPD Manifolds: Second-Order Geometric Representation Learning
Yuhan Peng, Junwen Dong, Yuzhi Zeng +6
Graph neural networks face two fundamental challenges rooted in the linear structure of Euclidean vector spaces: (1) Current architectures represent geometry through vectors (direc…
Cross-Session Decoding of Neural Spiking Data via Task-Conditioned Latent Alignment
Canyang Zhao, Bolin Peng, J. Patrick Mayo +2
Training a high-performing neural decoder can be difficult when only limited data are available from a recording session. To address this challenge, we propose a Task-Conditioned L…
SPD Matrix Learning for Neuroimaging Analysis: Perspectives, Methods, and Challenges
Ce Ju, Reinmar Kobler, Antoine Collas +3
Neuroimaging provides essential tools for characterizing brain activity by quantifying connectivity strength between remote regions, using different modalities that capture differe…
Graph Neural Networks on SPD Manifolds for Motor Imagery Classification: A Perspective from the Time-Frequency Analysis
Ce Ju, Cuntai Guan
The motor imagery (MI) classification has been a prominent research topic in brain-computer interfaces based on electroencephalography (EEG). Over the past few decades, the perform…
HHHFL: Hierarchical Heterogeneous Horizontal Federated Learning for Electroencephalography
Dashan Gao, Ce Ju, Xiguang Wei +3
Electroencephalography (EEG) classification techniques have been widely studied for human behavior and emotion recognition tasks. But it is still a challenging issue since the data…
Socially Aware Kalman Neural Networks for Trajectory Prediction
Ce Ju, Zheng Wang, Xiaoyu Zhang
Trajectory prediction is a critical technique in the navigation of robots and autonomous vehicles. However, the complex traffic and dynamic uncertainties yield challenges in the ef…
Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry
Antoine Collas, Ce Ju, Nicolas Salvy +1
Generating realistic brain connectivity matrices is key to analyzing population heterogeneity in brain organization, understanding disease, and augmenting data in challenging class…