A unified ecosystem and workspace for large-scale federated learning, bridging the gap between centralized model evolution and decentralized edge intelligence.
A curated list of awesome edge computing, including Frameworks, Simulators, Tools, etc.
云边协同- collaborative inference 📚Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge
云边协同- collaborative inference📚工作汇总 📚 Collaborative Inference Work Summary
About DNN compression and acceleration on Edge Devices.
云边协同- collaborative inference📚Dynamic adaptive DNN surgery for inference acceleration on the edge
北京交通大学计算机科学与技术学院系统与网络实验室
Code for paper "Joint Architecture Design and Workload Partitioning for DNN Inference on Industrial IoT Clusters"
Simulation Codes for “Relay-Assisted Cooperative Federated Learning”
An auto scheduling system for stream data processing on distributed cloud-edge platforms
subMFL: Compatible subModel Generation for Federated Learning in Device Heterogeneous Environment
DisCEdge: Distributed Context Management for LLMs at the Edge
Code for paper "Automated Spatial-Temporal Graph Neural Network Search for Skeleton-based Human Action Recognition on Edge Devices"
Code for paper "Dynamic Deep Neural Network Inference via Adaptive Channel Skipping"
Code for paper "Classification-based Dynamic Network for Efficient Super-Resolution"
HERMES (Heterogeneous Application-Enabled Routing Middleware for Edge-IoT Systems) is a networking library for ESP8266, ESP32, and Raspberry Pi devices that enables self-organising multi-hop Wi-Fi networks. It combines routing with a middleware layer that allows applications to influence network behavior through custom metrics and policies.
Make an edge intelligence node based on STM32
FL-enabled architecture for scalable and proactive network slice impact classification in Intelligent Transportation Systems (ITS).
A lightweight quantization module for PyTorch models
An end-to-end TinyML asset monitoring pipeline that trains an ANN on vibrational telemetry data and applies post-training INT8 quantization for ultra-low-power microcontroller deployments.