DISCO is a code-free and installation-free browser platform that allows any non-technical user to collaboratively train machine learning models without sharing any private data.

An SDK for multi-agent collaborative perception.

[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception

Privacy Preserving Collaborative Encrypted Network Traffic Classification (Differential Privacy, Federated Learning, Membership Inference Attack, Encrypted Traffic Classification)

a collaborative collection of interview questions collected from both sides of the game: Interviewer(s) and Interviewee.

Secure collaborative training and inference for XGBoost.

Official PyTorch Implementation for DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis - CVPR 2022

NEBULA: A Platform for Decentralized Federated Learning

Official implementation of our work "Collaborative Fairness in Federated Learning."

Learning to Walk with Dual Agents for Knowledge Graph Reasoning (AAAI'22)

Collective Knowledge repository with actions to unify the access to different predictive analytics engines (scipy, R, DNN) from software, command line and web-services via CK JSON API:

[ICLR'25] Official Implementation of STAMP: Scalable Task And Model-agnostic Collaborative Perception

Fedstellar: A Platform for Decentralized Federated Learning

Official implementation of FedGAT: Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstruction (https://arxiv.org/abs/2502.04521)

A Collaborative Learning platform: cataloging and remixing of Open Educational Resources (OER), e-mentoring and e-tutoring, Learning Analytics (LA), and more.

Simple and efficient way to learn a new programming language.

[AAAI-24] TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients

Human-Agent Collaborative Deep Reinforcement Learning

The code for the paper "Incentivizing Collaboration in Machine Learning via Synthetic Data Rewards" AAAI'22 Oral Presentation.

Multi-agent reinforcement learning framework for Unity environments. Implements MAPPO, MASAC, MATD3, and MADDPG with comprehensive evaluation tools. Features sample-efficient training, competitive analysis, and pre-trained models achieving great performance in Tennis and Soccer environments.