FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution

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

38 traditional FL (tFL) or personalized FL (pFL) algorithms, 3 scenarios, and 24 datasets. www.pfllib.com/

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

LAG code for NeurIPS 2018

Python code for paper "Lazily Aggregated Quantized Gradient Innovation for Communication-Efficient Federated Learning"

Federated learning with model quantization

Code for "Adaptive Gradient Quantization for Data-Parallel SGD", published in NeurIPS 2020.

使用模型量化降低通信开销，动态调整量化比特，降低等待时间，提高收敛速度

Comprehensive study on the quantization of various CNN models, employing techniques such as Post-Training Quantization and Quantization Aware Training (QAT).

The layer-wise training convolutional neural networks using local loss for sensor based human activity recognition

[Engineering Applications of Artificial Intelligence, 2023] GTSNet: Flexible Architecture under Budget Constraint for Real-Time Human Activity Recognition from Wearable Sensor

Human Activity Recognition - WISDM's activity prediction dataset

The source code and collected data for the Meta-HAR (WWW 2021) paper.

Personalized federated learning codebase for research

3-layer-CNN and ResNet with OPPORTUNITY dataset, PAMAP2 dataset, UCI-HAR dataset, UniMiB-SHAR dataset, USC-HAD dataset, and WISDM dataset.

Deep learning, classification on the WISDM dataset

Four Federated learning datasets for Human Activity Recognition

Repo for MobiSys 2021 paper: "ClusterFL: A Similarity-Aware Federated Learning System for Human Activity Recognition".

experiment to replicate paper: LSTM-CNN Architecture for Human Activity Recognition

Fall Detection and Prediction using GRU and LSTM with Transfer Learning

Dateset for MobiAct/MobiFall

人体活动识别神经网络的训练与在STM32L475VG上的部署

Human Activity Recognition using LSTM-CNN model on raw data set.

本人的科研经验

[ICLR'21] FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

Code for the paper "Boosting the Federation: Cross-Silo Federated Learning without Gradient Descent"

利用网络上公开的数据构建一个小型的证券知识图谱/知识库