Deep Transfer Hashing for Adaptive Learning on Federated Streaming Data

TL;DR

This paper proposes a federated learning framework that integrates deep transfer hashing and transfer learning to enable resource-efficient, privacy-preserving, and scalable distributed prediction on streaming data, with applications in traffic event detection.

Contribution

It introduces a novel combination of federated learning, deep transfer hashing, and transfer learning to improve efficiency and scalability in distributed streaming data scenarios.

Findings

Enhanced model accuracy through transfer learning

Reduced communication costs via hash codes

Improved scalability and privacy preservation

Abstract

This extended abstract explores the integration of federated learning with deep transfer hashing for distributed prediction tasks, emphasizing resource-efficient client training from evolving data streams. Federated learning allows multiple clients to collaboratively train a shared model while maintaining data privacy - by incorporating deep transfer hashing, high-dimensional data can be converted into compact hash codes, reducing data transmission size and network loads. The proposed framework utilizes transfer learning, pre-training deep neural networks on a central server, and fine-tuning on clients to enhance model accuracy and adaptability. A selective hash code sharing mechanism using a privacy-preserving global memory bank further supports client fine-tuning. This approach addresses challenges in previous research by improving computational efficiency and scalability. Practical applications include Car2X event predictions, where a shared model is collectively trained to recognize traffic patterns, aiding in tasks such as traffic density assessment and accident detection. The research aims to develop a robust framework that combines federated learning, deep transfer hashing and transfer learning for efficient and secure downstream task execution.