The implementation of "Personalized Edge Intelligence via Federated Self- Knowledge Distillation".

Code Implementation and Informations about FedAS

Distilling Knowledge via Knowledge Review, CVPR 2021

[CVPR 2022 Oral] Code release for "Causality Inspired Representation Learning for Domain Generalization"

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

[ICLR'24] Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate

Source code for the experiments on the layer-wise linear mode connectivity in deep neural networks

[ICML 2024 spotlight] This repository contains the implementation details for the paper "Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Min…

Official Implementation of FedRCL (CVPR 2024)

Code for CVPR2023 DaFKD : Domain-aware Federated Knowledge Distillation

Configure one file for model heterogeneity. Consistent GPU memory usage for single or multiple clients.

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

FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning

The is the official implementation of ICCV 2023 paper "No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier".

A collection of research on knowledge graphs

Code that implements efficient knowledge graph extraction from the textual descriptions

OceanGraph: Knowledge Graph for Ocean Science

基于深度学习与Neo4j的军事装备知识图谱网页应用构建。本项目是一个军事武器知识图谱网页应用软件原型系统。该系统由数据爬虫、数据管理、数据处理、知识问答、新闻热点、词条查询和图谱展示七个功能模块组成。系统从互联网上爬取数据，并基于百度文心ERNIE 3.0模型对数据进行实体识别和关系抽取，将数据处理为三元组形式并存储到图数据库Neo4j中。通过数据管理和数据标注，并通过对Neo4j中的三元组…

QAonMilitaryKG，QaSystem based on military knowledge graph that stores in mongodb which is different from the previous one, 基于mongodb存储的军事领域知识图谱问答项目，包括飞行器、太空装备等8大类，100余小类，共计5800项的军事武器知识库，该项目不使用图数据库进…

Military knowledge graph

史上最大规模1.4亿知识图谱数据免费下载，知识图谱，通用知识图谱，融合了两千五百多万的实体，拥有亿级别的实体属性关系。

史上最大规模1.4亿中文知识图谱开源下载

领域知识图谱数据采集、数据处理以及可视化

A tutorial and implement of disease centered Medical knowledge graph and qa system based on it。知识图谱构建，自动问答，基于kg的自动问答。以疾病为中心的一定规模医药领域知识图谱，并以该知识图谱完成自动问答与分析服务。

[NeurIPS 2022] The official code for our NeurIPS 2022 paper "Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?".

[CVPR 2024] Official Repository for "FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning"