Federated Learning: Foundations and Hands-on Implementation

Last Date of Registration :  22nd June, 2026

Mode of the LAB Workshop: IN – PERSON at IISER Bhopal

Kindly fill the registration form attached below. Payment link will be sent to the eligible candidates.

SKU: IISER Bhopal | Date : 29th June - 4th July, 2026 Category:

Profile of the Instructor

Haroon Lone has been an Assistant Professor at IISER Bhopal since June 2021. He works in the system's domain, and his research focuses on using IoT and data analytics to solve research problems in applied domains such as Healthcare. He has a Ph.D. in CSE from IIIT Delhi. Before joining IISER Bhopal, he spent one year each at the University of Virginia and the University of South Dakota as a Postdoc and Visiting Assistant Professor, respectively.

List of Experiments conducted in the LAB Workshop

Name Description
Day 1: Set up the federated learning
environment and implement a centralized
baseline model by training an MNIST classifier
in PyTorch
● Setting up the environment
● Overview of Flower / PySyft / FedML
● Implement a centralized training baseline
● Participants train a baseline MNIST classifier in
PyTorch.
Day 2: Implement federated MNIST
classification and compare the performance of
centralized and federated learning approaches.
● Federated MNIST classification
● Compare centralized vs federated learning
Day 3: Simulate IID and non-IID client datasets
to study data heterogeneity and evaluate
model convergence and performance in
federated learning.
● Partitioning datasets into non-IID distributions
● Evaluating convergence
● Simulate non-IID client datasets
● Evaluate model performance under IID and
Non-IID data
Day 4:Implement differential privacy
mechanisms in federated learning and analyze
the impact of different privacy budgets on
model performance.
● Implement Differential Privacy
● Train the FL model with different privacy
budgets.
Day 5: Build a complete federated learning
pipeline using the Flower framework and run
experiments with multiple simulated clients.
● Participants implement federated learning
with the Flower framework.
● Run FL experiment with 10 simulated clients.
Day 6: Evaluation

Eligibility & Qualification Criteria

Eligibility & Qualification Criteria:

Eligibility criteria for participants:
1. Basic knowledge of Python programming and introductory machine learning concepts
(e.g., classification, model training, and evaluation). Familiarity with PyTorch/TensorFlow
is desirable but not mandatory.

Basic qualification:

● Degree they can be pursuing - Faculty members, PhD scholars, postgraduate
students, and senior undergraduate students (3rd or 4th year) in Computer
Science, Data Science, Artificial Intelligence, Electrical Engineering, or related
disciplines.

Fee for the LAB Workshop

Registration fee : Rs. 1000 

A refund of Rs. 800 will be provided to eligible candidates upon completion of the LAB Workshop.

Please note: No refunds will be issued after the registration deadline on 22nd June, 2026

LAB Workshop Session Details

Date of the Workshop : 29th June – 4th July, 2026

Mode of the Workshop : IN – PERSON at IISER Bhopal

 

  • Start date: 29th June, 2026
  • End date: 4th July, 2026
  • Exam date: 4th July, 2026

       

Since the lab workshop will be residential:

  • Cost/day (room+food) : To be paid at host institute

Instructions for the lab workshop: (Things to be brought, safety rules, etc):

We will be sending  this through email to only selected candidates. 

Mark Split for the workshop

Internal: 50/100 (i.e., Each day there will be a quiz exam comprising 10 points)
Final exam: 50/100

Contact Details for Enquiry

Contact details of person at host institute for students to ask queries regarding the lab workshop:

Name: Haroon R Lone
Designation: Assistant professor
Email id: haroon@iiserb.ac.in
Phone number: 0755-269-2656

 

Contact details for Registration queries:

Email ID: nptelplus-workshop@nptel.iitm.ac.in

Reviews

There are no reviews yet.

Be the first to review “Federated Learning: Foundations and Hands-on Implementation”