Decentralized Federated Learning Framework Privacy Preserving and Transport Supply Chain Optimization with Blockchain Anchoring
Abstract
This paper creates a decentralised learning system that combines Federated Learning (FL) with blockchain based provenance to allow the stakeholders in the supply chain to weight predictive models without revealing raw data and keeping privacy intact, but increasing transparency. The study asserts long standing issues of data sensitivity, competitive confidentiality, and low inter organisational trust, which generally inhibit collaborative analytics in practicum supply chains setting. The conceptualization of the proposed architecture includes FL, blockchain anchoring, Explainable AI, Large Language Models (LLMs) and Graph Neural Networks (GNNs), and the prototype is implemented in FL simulation, blockchain logging, and model evaluation because of the available practical resources. Eight heterogeneous supply chain datasets were preprocessed and then given out to simulate multiple client training with FedAvg aggregation algorithm, and a Python based blockchain ledger was utilised to record immutable model updates. These findings indicate that the federated model is able to perform equally as a centralised baseline on non IID data and preserve privacy, and offer a verifiable audit trail. In general, the paper illustrates that decentralised AI is a viable solution to supply chain optimisation and provides a roadmap of the future development of the solution using sophisticated modelling elements and scalable implementation plans.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.