Unveiling the Private: Federated Learning and Model Compression for Secure AI at the Edge
08-24, 13:45–14:25 (Asia/Kuala_Lumpur), JC 3

The talk will explore privacy in machine learning (ML) and how Federated Learning (FL) can be leveraged to address privacy concerns effectively. Federated Learning allows training machine learning models across multiple decentralized devices or servers holding local data samples without exchanging them.

He will demonstrate a real-time Federated Learning setup using Python (MPI for communication), showcasing the integration of advanced communication protocols to manage real-time interaction and parallel processing among the nodes.

It will also discuss how model compression techniques (like Pruning, Quantization, Binarization, etc) can complement Federated Learning, enabling the efficient deployment of privacy-preserving models on resource-constrained edge devices.

  1. Introduction: The Privacy vs. Power Struggle in ML
    - The challenges of data privacy in traditional centralized learning.
    - Introducing the tension between powerful models and user privacy
    - Introduction of FL and model compression as potential solutions.

  2. Federated Learning: Training Together, Protecting Privacy
    - Core concept of FL and its decentralized training paradigm
    - Privacy benefits of FL as compared to traditional methods.

  3. Real-Time Visualization with MPI: See It to Believe It
    - Introduction of MPI as a powerful tool for parallel communication between simulated user devices.
    - Demonstrate how MPI can be used to create virtual users for FL training.
    - Use MPI to showcase a live visualization of the FL training process.

  4. Making the Cut: Model Compression for Edge Devices
    - Discussion on the limitations of deploying complex models on resource-constrained edge devices.
    - Introduction of model compression techniques(Quantization, Pruning, etc) for reducing model size without compromising accuracy.
    - How can model compression be integrated with FL for efficient deployment on edge devices?

  5. Conclusion
    - Discussion on the potential of FL and model compression for secure AI deployments at the edge with its real-time applications
Gautam Jajoo

Gautam Jajoo, a fourth-year CS student at BITS Pilani, is an experienced Python developer focused on Federated Learning. He has worked with MIT Media Lab, Nantes Université, and ADAPT Lab. As a CloudCV member and Google Summer of Code admin, he is dedicated to making AI research more reproducible.