Searcharxiv⌕ Search

arXiv subjects

Shiva Raj Pokhrel

Publications and source records attributed to Shiva Raj Pokhrel.

53 records · Page 3Linked to original sources
arXiv2024

Quantum Federated Learning Experiments in the Cloud with Data Encoding

Quantum Federated Learning (QFL) is an emerging concept that aims to unfold federated learning (FL) over quantum networks, enabling collaborative quantum model training along with local data privacy. We explore the challenges of deploying QFL on cloud platforms, emphasizing quantum intricacies and platform limitations. The proposed data-encoding-driven QFL, with a proof of concept (GitHub Open Source) using genomic data sets on quantum simulators, shows promising results.

cs.LG↗
arXiv2023

Deakin RF-Sensing: Experiments on Correlated Knowledge Distillation for Monitoring Human Postures with Radios

In this work, we propose and develop a simple experimental testbed to study the feasibility of a novel idea by coupling radio frequency (RF) sensing technology with Correlated Knowledge Distillation (CKD) theory towards designing lightweight, near real-time and precise human pose monitoring systems. 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. To assure its efficacy, we implemented CKD for distilling logits in our integrated Software Defined Radio (SDR)-based experimental setup and investigated the RF-visual signal correlation. Our CKD-RF sensing technique is characterized by two modes - a camera-fed Teacher Class Network (e.g., images, videos) with an SDR-fed Student Class Network (e.g., RF signals). Specifically, our CKD model trains a dual multi-branch teacher and student network by distilling and fusing knowledge bases. The resulting CKD models are then subsequently used to identify the multimodal correlation and teach the student branch in reverse. Instead of simply aggregating their learnings, CKD training comprised multiple parallel transformations with the two domains, i.e., visual images and RF signals. Once trained, our CKD model can efficiently preserve privacy and utilize the multimodal correlated logits from the two different neural networks for estimating poses without using visual signals/video frames (by using only the RF signals).

cs.CV↗
arXiv2023

Performance Analysis and Evaluation of Post Quantum Secure Blockchained Federated Learning

Post-quantum security is critical in the quantum era. Quantum computers, along with quantum algorithms, make the standard cryptography based on RSA or ECDSA over FL or Blockchain vulnerable. The implementation of post-quantum cryptography (PQC) over such systems is poorly understood as PQC is still in its standardization phase. In this work, we propose a hybrid approach to employ PQC over blockchain-based FL (BFL), where we combine a stateless signature scheme like Dilithium (or Falcon) with a stateful hash-based signature scheme like the extended Merkle Signature Scheme (XMSS). We propose a linear-based formulaic approach to device role selection mechanisms based on multiple factors to address the performance aspect. Our holistic approach of utilizing a verifiable random function (VRF) to assist in the blockchain consensus mechanism shows the practicality of the proposed approaches. The proposed method and extensive experimental results contribute to enhancing the security and performance aspects of BFL systems.

cs.CR↗
arXiv2023

Improving Federated Aggregation with Deep Unfolding Networks

The performance of Federated learning (FL) is negatively affected by device differences and statistical characteristics between participating clients. To address this issue, we introduce a deep unfolding network (DUN)-based technique that learns adaptive weights that unbiasedly ameliorate the adverse impacts of heterogeneity. The proposed method demonstrates impressive accuracy and quality-aware aggregation. Furthermore, it evaluated the best-weighted normalization approach to define less computational power on the aggregation method. The numerical experiments in this study demonstrate the effectiveness of this approach and provide insights into the interpretability of the unbiased weights learned. 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. Codes and details are \href{https://github.com/shanikairoshi/Improved_DUN_basedFL_Aggregation}{here}.

cs.LG↗
arXiv2023

Quantum Federated Learning: Analysis, Design and Implementation Challenges

Quantum Federated Learning (QFL) has gained significant attention due to quantum computing and machine learning advancements. As the demand for QFL continues to surge, there is a pressing need to comprehend its intricacies in distributed environments. This paper aims to provide a comprehensive overview of the current state of QFL, addressing a crucial knowledge gap in the existing literature. We develop ideas for new QFL frameworks, explore diverse use cases of applications, and consider the critical factors influencing their design. The technical contributions and limitations of various QFL research projects are examined while presenting future research directions and open questions for further exploration.

quant-ph↗
arXiv2023

Decentralized Quantum Federated Learning for Metaverse: Analysis, Design and Implementation

With the emerging developments of the Metaverse, a virtual world where people can interact, socialize, play, and conduct their business, it has become critical to ensure that the underlying systems are transparent, secure, and trustworthy. To this end, we develop a decentralized and trustworthy quantum federated learning (QFL) framework. The proposed QFL leverages the power of blockchain to create a secure and transparent system that is robust against cyberattacks and fraud. In addition, the decentralized QFL system addresses the risks associated with a centralized server-based approach. With extensive experiments and analysis, we evaluate classical federated learning (CFL) and QFL in a distributed setting and demonstrate the practicality and benefits of the proposed design. Our theoretical analysis and discussions develop a genuinely decentralized financial system essential for the Metaverse. Furthermore, we present the application of blockchain-based QFL in a hybrid metaverse powered by a metaverse observer and world model. Our implementation details and code are publicly available 1.

cs.LG↗
arXiv2023

Post Quantum Secure Blockchain-based Federated Learning for Mobile Edge Computing

Mobile Edge Computing (MEC) has been a promising paradigm for communicating and edge processing of data on the move. 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. FL is advantageous for mobile devices with constrained connectivity since it requires model updates to be delivered to a central point instead of substantial amounts of data communication. For instance, FL in autonomous, connected vehicles can increase data diversity and allow model customization, and predictions are possible even when the vehicles are not connected (by exploiting their local models) for short times. However, existing synchronous FL and Blockchain incur extremely high communication costs due to mobility-induced impairments and do not apply directly to MEC networks. We propose a fully asynchronous Blockchained Federated Learning (BFL) framework referred to as BFL-MEC, in which the mobile clients and their models evolve independently yet guarantee stability in the global learning process. More importantly, we employ post-quantum secure features over BFL-MEC to verify the client's identity and defend against malicious attacks. All of our design assumptions and results are evaluated with extensive simulations.

cs.DC↗
arXiv2022

Fair and Efficient Distributed Edge Learning with Hybrid Multipath TCP

The bottleneck of distributed edge learning (DEL) over wireless has shifted from computing to communication, primarily the aggregation-averaging (Agg-Avg) process of DEL. The existing transmission control protocol (TCP)-based data networking schemes for DEL are application-agnostic and fail to deliver adjustments according to application layer requirements. As a result, they introduce massive excess time and undesired issues such as unfairness and stragglers. Other prior mitigation solutions have significant limitations as they balance data flow rates from workers across paths but often incur imbalanced backlogs when the paths exhibit variance, causing stragglers. To facilitate a more productive DEL, we develop a hybrid multipath TCP (MPTCP) by combining model-based and deep reinforcement learning (DRL) based MPTCP for DEL that strives to realize quicker iteration of DEL and better fairness (by ameliorating stragglers). Hybrid MPTCP essentially integrates two radical TCP developments: i) successful existing model-based MPTCP control strategies and ii) advanced emerging DRL-based techniques, and introduces a novel hybrid MPTCP data transport for easing the communication of the Agg-Avg process. Extensive emulation results demonstrate that the proposed hybrid MPTCP can overcome excess time consumption and ameliorate the application layer unfairness of DEL effectively without injecting additional inconstancy and stragglers.

cs.NI↗
arXiv2022

Understand-Before-Talk (UBT): A Semantic Communication Approach to 6G Networks

In Shannon theory, semantic aspects of communication were identified but considered irrelevant to the technical communication problems. Semantic communication (SC) techniques have recently attracted renewed research interests in (6G) wireless because they have the capability to support an efficient interpretation of the significance and meaning intended by a sender (or accomplishment of the goal) when dealing with multi-modal data such as videos, images, audio, text messages, and so on, which would be the case for various applications such as intelligent transportation systems where each autonomous vehicle needs to deal with real-time videos and data from a number of sensors including radars. A notable difficulty of existing SC frameworks lies in handling the discrete constraints imposed on the pursued semantic coding and its interaction with the independent knowledge base, which makes reliable semantic extraction extremely challenging. Therefore, we develop a new lightweight hashing-based semantic extraction approach to the SC framework, where our learning objective is to generate one-time signatures (hash codes) using supervised learning for low latency, secure and efficient management of the SC dynamics. We first evaluate the proposed semantic extraction framework over large image data sets, extend it with domain adaptive hashing and then demonstrate the effectiveness of "semantics signature" in bulk transmission and multi-modal data.

cs.IT↗
arXiv2022

A Survey of Distributed Ledger Technology for IoT Verticals

The Internet of Things (IoT) and Distributed ledger technology (DLT) have significantly changed our daily lives. Due to their distributed operational environment and naturally decentralized applications, the convergence of these two technologies indicates a more lavish arrangement for the future. This article develops a comprehensive survey to investigate and illustrate state-of-the-art DLT for various IoT use cases, from smart homes to autonomous vehicles and smart cities. We develop a novel framework for conducting a systematic and comprehensive review of DLT over IoT by extending the knowledge graph approach. With relevant insights from this review, we extract innovative and pragmatic techniques to DLT design that enable high-performance, sustainable, and highly scalable IoT systems. Our findings support designing an end-to-end IoT-native DLT architecture for the future that fully coordinates network-assisted functionalities.

cs.DC↗
arXiv2022

FAIR-BFL: Flexible and Incentive Redesign for Blockchain-based Federated Learning

Vanilla Federated learning (FL) relies on the centralized global aggregation mechanism and assumes that all clients are honest. This makes it a challenge for FL to alleviate the single point of failure and dishonest clients. 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). However, one problem in vanilla BFL is that its capabilities do not follow adopters' needs in a dynamic fashion. Besides, vanilla BFL relies on unverifiable clients' self-reported contributions like data size because checking clients' raw data is not allowed in FL for privacy concerns. We design and evaluate a novel BFL framework, and resolve the identified challenges in vanilla BFL with greater flexibility and incentive mechanism called FAIR-BFL. In contrast to existing works, FAIR-BFL offers unprecedented flexibility via the modular design, allowing adopters to adjust its capabilities following business demands in a dynamic fashion. Our design accounts for BFL's ability to quantify each client's contribution to the global learning process. Such quantification provides a rational metric for distributing the rewards among federated clients and helps discover malicious participants that may poison the global model.

cs.DC↗
arXiv2021

Learning to Harness Bandwidth with Multipath Congestion Control and Scheduling

Multipath TCP (MPTCP) has emerged as a facilitator for harnessing and pooling available bandwidth in wireless/wireline communication networks and in data centers. Existing implementations of MPTCP such as, Linked Increase Algorithm (LIA), Opportunistic LIA (OLIA) and BAlanced LInked Adaptation (BALIA) include separate algorithms for congestion control and packet scheduling, with pre-selected control parameters. We propose a Deep Q-Learning (DQL) based framework for joint congestion control and packet scheduling for MPTCP. At the heart of the solution is an intelligent agent for interface, learning and actuation, which learns from experience optimal congestion control and scheduling mechanism using DQL techniques with policy gradients. We provide a rigorous stability analysis of system dynamics which provides important practical design insights. In addition, the proposed DQL-MPTCP algorithm utilizes the `recurrent neural network' and integrates it with `long short-term memory' for continuously i) learning dynamic behavior of subflows (paths) and ii) responding promptly to their behavior using prioritized experience replay. With extensive emulations, we show that the proposed DQL-based MPTCP algorithm outperforms MPTCP LIA, OLIA and BALIA algorithms. Moreover, the DQL-MPTCP algorithm is robust to time-varying network characteristics, and provides dynamic exploration and exploitation of paths.

cs.NI↗
arXiv2021

Modeling RIS Empowered Outdoor-to-Indoor Communication in mmWave Cellular Networks

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. To address this, we investigate the practicability of utilizing reconfigurable intelligent surfaces (RISs) for assisting such O2I communication. We propose a new notion of prefabricated RIS-empowered wall consisting of a large number of chipless radio frequency identification (RFID) sensors. Each sensor maintains its own bank of delay lines. These sensors which are built within the building walls can potentially be controlled by a main integrated circuit (IC) to regulate the phase of impinging signals. To evaluate our idea, we develop a thorough performance analysis of the RIS-based O2I communication in the mmWave network using stochastic-geometry tools for blockage models. Our analysis facilitates two closed-form approximations of the downlink signal-to-noise ratio (SNR) coverage probability for RIS-based O2I communication. We perform extensive simulations to evaluate the accuracy of the derived expressions, thus providing new observations and findings.

eess.SP↗
arXiv2020

Towards Enabling Critical mMTC: A Review of URLLC within mMTC

Massive machine-type communication (mMTC) and ultra-reliable and low-latency communication (URLLC) are two key service types in the fifth-generation (5G) communication systems, pursuing scalability and reliability with low-latency, respectively. These two extreme services are envisaged to agglomerate together into \emph{critical mMTC} shortly with emerging use cases (e.g., wide-area disaster monitoring, wireless factory automation), creating new challenges to designing wireless systems beyond 5G. While conventional network slicing is effective in supporting a simple mixture of mMTC and URLLC, it is difficult to simultaneously guarantee the reliability, latency, and scalability requirements of critical mMTC (e.g., < 4ms latency, $10^6$ devices/km$^2$ for factory automation) with limited radio resources. Furthermore, recently proposed solutions to scalable URLLC (e.g., machine learning aided URLLC for driverless vehicles) are ill-suited to critical mMTC whose machine type users have minimal energy budget and computing capability that should be (tightly) optimized for given tasks. To this end, our paper aims to characterize promising use cases of critical mMTC and search for their possible solutions. To this end, we first review the state-of-the-art (SOTA) technologies for separate mMTC and URLLC services and then identify key challenges from conflicting SOTA requirements, followed by potential approaches to prospective critical mMTC solutions at different layers.

cs.NI↗
arXiv2020

Optimal Centralized Dynamic-Time-Division-Duplex

In this paper, we derive the optimal centralized dynamic-time-division-duplex (D-TDD) scheme for a wireless network comprised of $K$ full-duplex nodes impaired by self-interference and additive white Gaussian noise. As a special case, we also provide the optimal centralized D-TDD scheme when the nodes are half-duplex as well as when the wireless network is comprised of both half-duplex and full-duplex nodes. Thereby, we derive the optimal adaptive scheduling of the reception, transmission, simultaneous reception and transmission, and silence at every node in the network in each time slot such that the rate region of the network is maximized. The performance of the optimal centralized D-TDD can serve as an upper-bound to any other TDD scheme, which is useful in qualifying the relative performance of TDD schemes. The numerical results show that the proposed centralized D-TDD scheme achieves significant rate gains over existing centralized D-TDD schemes.

cs.IT↗
arXiv2019

Federated learning with multichannel ALOHA

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. We show that multichannel random access can provide a better performance than sequential polling when some users are unable to compute local updates (due to other tasks) or in dormant state. In addition, for better aggregation in federated learning, the access probabilities of users can be optimized for given local updates. To this end, we formulate an optimization problem and show that a distributed approach can be used within federated learning to adaptively decide the access probabilities.

cs.IT↗