no code implementations • 30 Jun 2023 • Shanika I Nanayakkara, Shiva Raj Pokhrel, Gang Li
By incorporating unbiased weights into the model, the proposed approach effectively addresses quality-aware aggregation under the heterogeneity of the participating clients and the FL environment.
no code implementations • 27 Jun 2023 • Dev Gurung, Shiva Raj Pokhrel, Gang Li
Quantum Federated Learning (QFL) has gained significant attention due to quantum computing and machine learning advancements.
1 code implementation • 20 Jun 2023 • Dev Gurung, Shiva Raj Pokhrel, Gang Li
To this end, we develop a decentralized and trustworthy quantum federated learning (QFL) framework.
no code implementations • 24 May 2023 • Shiva Raj Pokhrel, Jonathan Kua, Deol Satish, Philip Williams, Arkady Zaslavsky, Seng W. Loke, Jinho Choi
The proposed CKD framework transfers and fuses pose knowledge from a robust "Teacher" model to a parameterized "Student" model, which can be a promising technique for obtaining accurate yet lightweight pose estimates.
1 code implementation • 26 Apr 2023 • Dev Gurung, Shiva Raj Pokhrel, Gang Li
We design a model of Post Quantum Cryptography (PQC) Quantum Federated Learning (QFL).
1 code implementation • 26 Feb 2023 • Rongxin Xu, Shiva Raj Pokhrel, Qiujun Lan, Gang Li
We aim to employ Federated Learning (FL) and prominent features of blockchain into MEC architecture such as connected autonomous vehicles to enable complete decentralization, immutability, and rewarding mechanisms simultaneously.
no code implementations • 3 Nov 2022 • Shiva Raj Pokhrel, Jinho Choi, Anwar Walid
The bottleneck of distributed edge learning (DEL) over wireless has shifted from computing to communication, primarily the aggregation-averaging (Agg-Avg) process of DEL.
no code implementations • 26 Jun 2022 • Rongxin Xu, Shiva Raj Pokhrel, Qiujun Lan, Gang Li
These impending challenges in the design philosophy of FL call for blockchain-based federated learning (BFL) due to the benefits of coupling FL and blockchain (e. g., democracy, incentive, and immutability).
Ranked #1 on Malicious Detection on MNIST
no code implementations • 4 Jan 2021 • Mahyar Nemati, Behrouz Maham, Shiva Raj Pokhrel, Jinho Choi
With the increasing adoption of millimeter-waves (mmWave) over cellular networks, outdoor-to-indoor (O2I) communication has been one of the challenging research problems due to high penetration loss of buildings.
no code implementations • 13 Dec 2019 • Jinho Choi, Shiva Raj Pokhrel
In this paper, we study federated learning in a cellular system with a base station (BS) and a large number of users with local data sets.
Information Theory Signal Processing Information Theory