arXiv subjects

Rahif Kassab

Publications and source records attributed to Rahif Kassab.

11 recordsLinked to original sources

arXiv2022

Client Selection for Federated Bayesian Learning

Distributed Stein Variational Gradient Descent (DSVGD) is a non-parametric distributed learning framework for federated Bayesian learning, where multiple clients jointly train a machine learning model by communicating a number of non-random and interacting particles with the server. Since communication resources are limited, selecting the clients with most informative local learning updates can improve the model convergence and communication efficiency. In this paper, we propose two selection schemes for DSVGD based on Kernelized Stein Discrepancy (KSD) and Hilbert Inner Product (HIP). We derive the upper bound on the decrease of the global free energy per iteration for both schemes, which is then minimized to speed up the model convergence. We evaluate and compare our schemes with conventional schemes in terms of model accuracy, convergence speed, and stability using various learning tasks and datasets.

cs.LG↗

arXiv2021

Forget-SVGD: Particle-Based Bayesian Federated Unlearning

Variational particle-based Bayesian learning methods have the advantage of not being limited by the bias affecting more conventional parametric techniques. This paper proposes to leverage the flexibility of non-parametric Bayesian approximate inference to develop a novel Bayesian federated unlearning method, referred to as Forget-Stein Variational Gradient Descent (Forget-SVGD). Forget-SVGD builds on SVGD - a particle-based approximate Bayesian inference scheme using gradient-based deterministic updates - and on its distributed (federated) extension known as Distributed SVGD (DSVGD). Upon the completion of federated learning, as one or more participating agents request for their data to be "forgotten", Forget-SVGD carries out local SVGD updates at the agents whose data need to be "unlearned", which are interleaved with communication rounds with a parameter server. The proposed method is validated via performance comparisons with non-parametric schemes that train from scratch by excluding data to be forgotten, as well as with existing parametric Bayesian unlearning methods.

cs.LG↗

arXiv2020

Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descent

This paper introduces Distributed Stein Variational Gradient Descent (DSVGD), a non-parametric generalized Bayesian inference framework for federated learning. DSVGD maintains a number of non-random and interacting particles at a central server to represent the current iterate of the model global posterior. The particles are iteratively downloaded and updated by one of the agents with the end goal of minimizing the global free energy. By varying the number of particles, DSVGD enables a flexible trade-off between per-iteration communication load and number of communication rounds. DSVGD is shown to compare favorably to benchmark frequentist and Bayesian federated learning strategies, also scheduling a single device per iteration, in terms of accuracy and scalability with respect to the number of agents, while also providing well-calibrated, and hence trustworthy, predictions.

cs.LG↗

arXiv2020

Fog-Based Detection for Random-Access IoT Networks with Per-Measurement Preambles

Internet of Things (IoT) systems may be deployed to monitor spatially distributed quantities of interests (QoIs), such as noise or pollution levels. This paper considers a fog-based IoT network, in which active IoT devices transmit measurements of the monitored QoIs to the local edge node (EN), while the ENs are connected to a cloud processor via limited-capacity fronthaul links. While the conventional approach uses preambles as metadata for reserving communication resources, here we consider assigning preambles directly to measurement levels across all devices. The resulting Type-Based Multiple Access (TBMA) protocol enables the efficient remote detection of the QoIs, rather than of the individual payloads. The performance of both edge and cloud-based detection or hypothesis testing is evaluated in terms of error exponents. Cloud-based hypothesis testing is shown theoretically and via numerical results to be advantageous when the inter-cell interference power and the fronthaul capacity are sufficiently large.

cs.IT↗

arXiv2020

Multi-Agent Deep Stochastic Policy Gradient for Event Based Dynamic Spectrum Access

We consider the dynamic spectrum access (DSA) problem where $K$ Internet of Things (IoT) devices compete for $T$ time slots constituting a frame. Devices collectively monitor $M$ events where each event could be monitored by multiple IoT devices. Each device, when at least one of its monitored events is active, picks an event and a time slot to transmit the corresponding active event information. In the case where multiple devices select the same time slot, a collision occurs and all transmitted packets are discarded. In order to capture the fact that devices observing the same event may transmit redundant information, we consider the maximization of the average sum event rate of the system instead of the classical frame throughput. We propose a multi-agent reinforcement learning approach based on a stochastic version of Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to access the frame by exploiting device-level correlation and time correlation of events. Through numerical simulations, we show that the proposed approach is able to efficiently exploit the aforementioned correlations and outperforms benchmark solutions such as standard multiple access protocols and the widely used Independent Deep Q-Network (IDQN) algorithm.

cs.IT↗

arXiv2020

Grant-Free Coexistence of Critical and Non-Critical IoT Services in Two-Hop Satellite and Terrestrial Networks

Terrestrial and satellite communication networks often rely on two-hop wireless architectures with an access channel followed by backhaul links. Examples include Cloud-Radio Access Networks (C-RAN) and Low-Earth Orbit (LEO) satellite systems. Furthermore, communication services characterized by the coexistence of heterogeneous requirements are emerging as key use cases. This paper studies the performance of critical service (CS) and non-critical service (NCS) for Internet of Things (IoT) systems sharing a grant-free channel consisting of radio access and backhaul segments. On the radio access segment, IoT devices send packets to a set of non-cooperative access points (APs) using slotted ALOHA (SA). The APs then forward correctly received messages to a base station over a shared wireless backhaul segment adopting SA. We study first a simplified erasure channel model, which is well suited for satellite applications. Then, in order to account for terrestrial scenarios, the impact of fading is considered. Among the main conclusions, we show that orthogonal inter-service resource allocation is generally preferred for NCS devices, while non-orthogonal protocols can improve the throughput and packet success rate of CS devices for both terrestrial and satellite scenarios.

cs.IT↗

arXiv2019

Non-Orthogonal eMBB-URLLC Radio Access for Cloud Radio Access Networks with Analog Fronthauling

This paper considers the coexistence of Ultra Reliable Low Latency Communications (URLLC) and enhanced Mobile BroadBand (eMBB) services in the uplink of Cloud Radio Access Network (C-RAN) architecture based on the relaying of radio signals over analog fronthaul links. While Orthogonal Multiple Access (OMA) to the radio resources enables the isolation and the separate design of different 5G services, Non-Orthogonal Multiple Access (NOMA) can enhance the system performance by sharing wireless and fronthaul resources. This paper provides an information-theoretic perspective in the performance of URLLC and eMBB traffic under both OMA and NOMA. The analysis focuses on standard cellular models with additive Gaussian noise links and a finite inter-cell interference span, and it accounts for different decoding strategies such as puncturing, Treating Interference as Noise (TIN) and Successive Interference Cancellation (SIC). Numerical results demonstrate that, for the considered analog fronthauling C-RAN architecture, NOMA achieves higher eMBB rates with respect to OMA, while guaranteeing reliable low-rate URLLC communication with minimal access latency. Moreover, NOMA under SIC is seen to achieve the best performance, while, unlike the case with digital capacity-constrained fronthaul links, TIN always outperforms puncturing.

cs.IT↗

arXiv2019

Space Diversity-Based Grant-Free Random Access for Critical and Non-Critical IoT Services

In this paper, we study the coexistence of critical and non-critical Internet of Things (IoT) services on a grant-free channel consisting of radio access and backhaul segments. On the radio access segment, IoT devices send packets to access points (APs) over an erasure collision channel using the slotted ALOHA protocol. Then, the APs forward correctly received messages to a base station (BS) over a shared wireless backhaul segment, modeled as an erasure collision channel. The APs hence play the role of uncoordinated relays that provide space diversity and may reduce performance losses caused by collisions. Both non-orthogonal and inter-service orthogonal resource sharing are considered and compared. Throughput and reliability metrics are analyzed, and numerical results are provided to assess the performance trade-offs between critical and non-critical IoT services.

cs.NI↗

arXiv2019

Information-Centric Grant-Free Access for IoT Fog Networks: Edge vs Cloud Detection and Learning

A multi-cell Fog-Radio Access Network (F-RAN) architecture is considered in which Internet of Things (IoT) devices periodically make noisy observations of a Quantity of Interest (QoI) and transmit using grant-free access in the uplink. The devices in each cell are connected to an Edge Node (EN), which may also have a finite-capacity fronthaul link to a central processor. In contrast to conventional information-agnostic protocols, the devices transmit using a Type-Based Multiple Access (TBMA) protocol that is tailored to enable the estimate of the field of correlated QoIs in each cell based on the measurements received from IoT devices. In this paper, this form of information-centric radio access is studied for the first time in a multi-cell F-RAN model with edge or cloud detection. Edge and cloud detection are designed and compared for a multi-cell system. Optimal model-based detectors are introduced and the resulting asymptotic behavior of the probability of error at cloud and edge is derived. Then, for the scenario in which a statistical model is not available, data-driven edge and cloud detectors are discussed and evaluated in numerical results.

cs.IT↗

arXiv2018

Non-Orthogonal Multiplexing of Ultra-Reliable and Broadband Services in Fog-Radio Architectures

The fifth generation (5G) of cellular systems is introducing Ultra-Reliable Low-Latency Communications (URLLC) services alongside more conventional enhanced Mobile BroadBand (eMBB) traffic. Furthermore, the 5G cellular architecture is evolving from a base station-centric deployment to a fog-like set-up that accommodates a flexible functional split between cloud and edge. In this paper, a novel solution is proposed that enables the non-orthogonal coexistence of URLLC and eMBB services by processing URLLC traffic at the Edge Nodes (ENs), while eMBB communications are handled centrally at a cloud processor as in a Cloud-Radio Access Network (C-RAN) system. This solution guarantees the low-latency requirements of the URLLC service by means of edge processing, e.g., for vehicle-to-cellular use cases, as well as the high spectral efficiency for eMBB traffic via centralized baseband processing. Both uplink and downlink are analyzed by accounting for the heterogeneous performance requirements of eMBB and URLLC traffic and by considering practical aspects such as fading, lack of channel state information for URLLC transmitters, rate adaptation for eMBB transmitters, finite fronthaul capacity, and different coexistence strategies, such as puncturing.

cs.NI↗

arXiv2018

Coexistence of URLLC and eMBB services in the C-RAN Uplink: An Information-Theoretic Study

The performance of orthogonal and non-orthogonal multiple access is studied for the multiplexing of enhanced Mobile BroadBand (eMBB) and Ultra-Reliable Low-Latency Communications (URLLC) users in the uplink of a multi-cell Cloud Radio Access Network (C-RAN) architecture. While eMBB users can operate over long codewords spread in time and frequency, URLLC users' transmissions are random and localized in time due to their low-latency requirements. These requirements also call for decoding of their packets to be carried out at the edge nodes (ENs), whereas eMBB traffic can leverage the interference management capabilities of centralized decoding at the cloud. Using information-theoretic arguments, the performance trade-offs between eMBB and URLLC traffic types are investigated in terms of rate for the former, and rate, access latency, and reliability for the latter. The analysis includes non-orthogonal multiple access (NOMA) with different decoding architectures, such as puncturing and successive interference cancellation (SIC). The study sheds light into effective design choices as a function of inter-cell interference, signal-to-noise ratio levels, and fronthaul capacity constraints.

cs.NI↗