Decentralized Federated Learning Platform

A blockchain-based federated learning platform built on NEAR Protocol that enables decentralized machine learning model training while preserving data privacy.

Features

• Decentralized model training using federated learning
• Privacy-preserving data handling
• NEAR blockchain integration for transparency and incentives
• Real-time model status tracking
• Participant management system
• Reward distribution mechanism

Flow Diagram

graph TB
subgraph Frontend
UI[User Interface]
ML[TensorFlow.js Model]
WI[Wallet Integration]
subgraph ML Components
PP[Data Preprocessing]
TR[Model Training]
DP[Differential Privacy]
end
UI --> WI
UI --> ML
ML --> PP
ML --> TR
TR --> DP
end
subgraph Smart Contract
PR[Participant Registry]
MU[Model Updates]
RD[Reward Distribution]
MS[Model Status]
end
subgraph NEAR Protocol
BC[Blockchain]
WL[Wallet]
end
%% Frontend to Smart Contract Interactions
WI --> WL
DP --> MU
UI --> PR
UI --> MS
%% Smart Contract to Blockchain
PR --> BC
MU --> BC
RD --> BC
MS --> BC
%% Blockchain to Wallet
BC --> WL
style Frontend fill:#f9f9f9,stroke:#333,stroke-width:2px
style Smart Contract fill:#e6f3ff,stroke:#333,stroke-width:2px
style NEAR Protocol fill:#f0fff0,stroke:#333,stroke-width:2px?

Loading

Tech Stack

• Frontend: Next.js, TypeScript, TailwindCSS
• Smart Contract: Rust, near-sdk
• Blockchain: NEAR
• Machine Learning: TensorFlow.js

Prerequisites

• Node.js >= 16
• Rust toolchain
• NEAR CLI
• A NEAR testnet account

Installation

1. Clone the repository:

git clone https://github.com/kamalbuilds/decentralised-federated-learning-platform
cd decentralised-federated-learning-platform

2. Install frontend dependencies:

cd frontend
npm install

3. Build the smart contract:

cd contract
cargo near build

Smart Contract Deployment

1. Login to your NEAR testnet account:

near login

2. Deploy the contract:

near deploy --accountId your-testnet-account.testnet --wasmFile target/wasm32-unknown-unknown/release/contract.wasm

Running the Application

1. Start the frontend development server:

cd frontend
npm run dev

2. Open your browser and navigate to http://localhost:3000

Usage

1. Connect Wallet: Click "Connect Wallet" to link your NEAR account

2. Register as Participant: Register to participate in the federated learning process

3. Train Model: Contribute to model training using your local data

4. View Status: Monitor training progress and model updates

5. Receive Rewards: Earn rewards for successful contributions

Architecture

Smart Contract

• Manages participant registration
• Handles model updates
• Distributes rewards
• Maintains training status

Frontend

• User interface for model training
• Wallet integration
• Real-time status updates
• Training visualization

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details

Acknowledgments

• NEAR Protocol team
• Federated Learning community
• Open source contributors