NIT Delhi | Internship on Federated Learning for User Privacy and Data Confidentiality, Apply by 10th February 2024!
Overview:
Department of Computer Science & Engineering, NIT Delhi is inviting applications for an Internship on Federated Learning for User Privacy and Data Confidentiality. Interested ones can apply. It allows participants from academic institutions, industry professionals, and researchers to discuss and develop an understanding of various issues arising due to tremendous growth in proposed areas.
Objective:
-
This Training and Internship will include invited talks by eminent speakers, academicians, and industry experts.
-
To enable open collaboration among federated learning (FL) co-creators and enhance the adoption of the FL paradigm, we envision that communities of data owners must self-organize during FL model training based on diverse notions of trustworthy federated learning, which include, but not limited to, security and robustness, privacy-preservation, interpretability, fairness, verifiability, transparency, incremental aggregation of shared learned models, and creating healthy market mechanisms to enable open dynamic collaboration among data owners under the FL paradigm.
Nature of Support (if approved):
-
Daily necessary expenses such as travel, stationery, consumables, accommodation, food, etc. for the participating students will be borne by the host institute through SERB funding support.
-
The participating students will also be eligible for TA reimbursement for their journey to the host institute from their hometown/home institute, both ways, as per GoI norms.
-
The applicants have to produce a letter of authentication from their Supervisor / Head of the Department / Head of the Institute indicating their association with the Institute and a “No Objection Certificate (NOC)” for allowing their student to undergo an internship if selected.
Important Dates:
Online registration should be made on and after Feb. 10, 2024.
Course Contents:
-
Federated Machine Learning System Models & Design
-
Transfer Learning in Federated Learning
-
Optimization Algorithms for Network Management in Federated Learning
-
Incentive Mechanisms for Federated Learning Participants
-
Deep Reinforcement Learning for Federated Learning Resource Management
-
Routing Schemes in Federated Learning
-
Federated Learning Client Selection and Scheduling
-
Datasets and open-source tools for federated and privacy-preserving web search and data mining.
-
Applications of Federated Learning in Wireless Networks (5G, 6G), Internet of Things, Cloud/Fog/Edge Computing and Networks, Vehicular and Mobile Networks, Urban Environments, Smart Cities, Healthcare, etc.
-
Platforms Addressing Security and Privacy Concerns in Federated Learning