A5069440857- Privacy-Preserving Technologies in Data
- Human Mobility and Location-Based Analysis
- Traffic Prediction and Management Techniques
- Mobile Crowdsensing and Crowdsourcing
- Privacy, Security, and Data Protection
- Anomaly Detection Techniques and Applications
- Complex Systems and Time Series Analysis
- Time Series Analysis and Forecasting
- Domain Adaptation and Few-Shot Learning
- Adversarial Robustness in Machine Learning
- Image and Video Quality Assessment
Nanjing University
2021-2023
Federated learning has emerged as a promising distributed machine paradigm to preserve data privacy. One of the fundamental challenges federated is that samples across clients are usually not independent and identically (non-IID), leading slow convergence severe performance drop aggregated global model. To facilitate model aggregation on non-IID data, it desirable infer unknown distributions without violating privacy protection policy. In this paper, we propose novel data-agnostic...
Federated learning (FL) has been proposed as a novel paradigm to enable distributed on the edge with privacy protection. However, existing federated approaches mainly focus training deep classification and clustering models, no enough attention paid solve reinforcement task edge, challenging where multiple agents observe local state take actions train global model without revealing their dataset. In this paper, we propose generalised framework called FedMC that integrates models trained by...
Multivariate time series (MTS) clustering is an important technique for discovering co-evolving patterns and interpreting group characteristics in many areas including economics, bioinformatics, data science, etc. Although has been widely studied the past decades, no enough attention paid to capture time-varying correlation MTS. In this article, we propose a novel approach MTS based on features. We introduce Gaussian Markov Random Fields (T-GMRF) model describe structure between variables,...