TsingZ0

PFLlib. Master Federated Learning in 2 Hours—Run It on Your PC!

HtFLlib. You only need to configure one file to support model heterogeneity. Consistent GPU memory usage for single or multiple clients.

FedALA. AAAI 2023 accepted paper, FedALA: Adaptive Local Aggregation for Personalized Federated Learning

FedTGP. AAAI 2024 accepted paper, FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning

FL-IoT. This is a platform containing the datasets and federated learning algorithms in IoT environments.

FedKTL. CVPR 2024 accepted paper, An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning

FedCP. KDD 2023 accepted paper, FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy

TLSAN. This is our implementation for our paper: TLSAN: Time-aware Long- and Short-term Attention Network for Next-item Recommendation

GPFL. ICCV 2023 accepted paper, GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning

DBE. NeurIPS 2023 accepted paper, Eliminating Domain Bias for Federated Learning in Representation Space

EvolveGen. Cloud-Edge Collaboration Platform for Automated Synthetic Dataset Generation

PCEvolve. ICML 2025 Spotlight, PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs

AP2O. AAAI'26, AP2O-Coder: Adaptively Progressive Preference Optimization for Reducing Compilation and Runtime Errors in LLM-Generated Code

SHAN. This is the implementation for the paper: Sequential Recommender System based on Hierarchical Attention Network

FedL2G. Adaptive Guidance for Local Training in Heterogeneous Federated Learning

TsingZ0. About me.

HtFL-OnDevice. Run your HtFL methods on physical single-board computers and mobile phones under identical environments and configurations.

ICE6405P-260-M01. Course materials

LSPM. This is the implementation for the paper: Online Personalized Next-Item Recommendation via Long Short Term Preference Learning

BSTS. This is the implementation for Web Search & Mining course, which contains data crawling (Ubuntu IRC data (2004~2021)) and preprocessing, boolean search, spell-correction with tolerant (fuzzy) search and simple web interface

verl-A2R. Python