FPFerdous Pervej

Ferdous Pervej

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ferdous Pervej has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Efficient Split Learning With Overlapping Areas: Handling Distribution Shift in Multi-Cell Networks

    by Atif Rizwan, Dong-Jun Han, Ferdous Pervej, Christopher G. Brinton, Andreas F. Molisch, Minseok Choi

    In multi-cell wireless networks, providing intelligent services via federated learning (FL) becomes more challenging due to multi-level distribution shifts across clients and regions, as well as additional communication delays among edge and cloud servers. To address these issues, we propose SplitOMC, a split learning framework that integrates overlapping-area clients and a multi-exit neural architecture to jointly handle (i) client-preferred, (ii) out-of-preference, and (iii) out-of-region tasks. By strategically leveraging clients in overlapping regions, SplitOMC accelerates training without excessive backhaul communication, while maintaining both personalization and generalization. We theoretically analyze the convergence behavior of the proposed algorithm, ensuring performance stability under heterogeneous data and communication conditions. Extensive experiments on MNIST, CIFAR-10/100, and a real-world Jetson Nano testbed demonstrate that SplitOMC consistently achieves faster training and inference with improved accuracy compared to state-of-the-art methods. In particular, the framework shows robustness in resource-constrained and unstable network environments, highlighting its practical value for next-generation wireless intelligent services.


  • Resource-Aware Hierarchical Federated Learning in Wireless Video Caching Networks

    by Ferdous Pervej, Andreas F. Molisch

    Backhaul traffic congestion caused by the video traffic of a few popular files can be alleviated by storing the to-be-requested content at various levels in wireless video caching networks. Typically, content service providers (CSPs) own the content, and the users request their preferred content from the CSPs using their (wireless) internet service providers (ISPs). As these parties do not reveal their private information and business secrets, traditional techniques may not be readily used to predict the dynamic changes in users’ future demands. Motivated by this, we propose a novel resource-aware hierarchical federated learning (RawHFL) solution for predicting user’s future content requests. A practical data acquisition technique is used that allows the user to update its local training dataset based on its requested content. Besides, since networking and other computational resources are limited, considering that only a subset of the users participate in the model training, we derive the convergence bound of the proposed algorithm. Based on this bound, we minimize a weighted utility function for jointly configuring the controllable parameters to train the RawHFL energy efficiently under practical resource constraints. Our extensive simulation results validate the proposed algorithm’s superiority, in terms of test accuracy and energy cost, over existing baselines.


  • Hierarchical Federated Learning in Wireless Networks: Pruning Tackles Bandwidth Scarcity and System Heterogeneity

    by Ferdous Pervej, Richeng Jin, Huaiyu Dai

    While a practical wireless network has many tiers where end users do not directly communicate with the central server, the users’ devices have limited computation and battery powers, and the serving base station (BS) has a fixed bandwidth. Owing to these practical constraints and system models, this paper leverages model pruning and proposes a pruning-enabled hierarchical federated learning (PHFL) in heterogeneous networks (HetNets). We first derive an upper bound of the convergence rate that clearly demonstrates the impact of the model pruning and wireless communications between the clients and the associated BS. Then we jointly optimize the model pruning ratio, central processing unit (CPU) frequency and transmission power of the clients in order to minimize the controllable terms of the convergence bound under strict delay and energy constraints. However, since the original problem is not convex, we perform successive convex approximation (SCA) and jointly optimize the parameters for the relaxed convex problem. Through extensive simulation, we validate the effectiveness of our proposed PHFL algorithm in terms of test accuracy, wall clock time, energy consumption and bandwidth requirement.


  • Efficient Content Delivery in User-Centric and Cache-Enabled Vehicular Edge Networks with Deadline-Constrained Heterogeneous Demands

    by Ferdous Pervej, Richeng Jin, Shih-Chun Lin, Huaiyu Dai

    Modern connected vehicles (CVs) frequently require diverse types of content for mission-critical decision-making and onboard users' entertainment. These contents are required to be fully delivered to the requester CVs within stringent deadlines that the existing radio access technology (RAT) solutions may fail to ensure. Motivated by the above consideration, this paper exploits content caching in vehicular edge networks (VENs) with a software-defined user-centric virtual cell (VC) based RAT solution for delivering the requested contents from a proximity edge server. Moreover, to capture the heterogeneous demands of the CVs, we introduce a preference-popularity tradeoff in their content request model. To that end, we formulate a joint optimization problem for content placement, CV scheduling, VC configuration, VC-CV association and radio resource allocation to minimize long-term content delivery delay. However, the joint problem is highly complex and cannot be solved efficiently in polynomial time. As such, we decompose the original problem into a cache placement problem and a content delivery delay minimization problem given the cache placement policy. We use deep reinforcement learning (DRL) as a learning solution for the first sub-problem. Furthermore, we transform the delay minimization problem into a priority-based weighted sum rate (WSR) maximization problem, which is solved leveraging maximum bipartite matching (MWBM) and a simple linear search algorithm. Our extensive simulation results demonstrate the effectiveness of the proposed method compared to existing baselines in terms of cache hit ratio (CHR), deadline violation and content delivery delay.


  • Top Cited Papers

    Resource Constrained Vehicular Edge Federated Learning With Highly Mobile Connected Vehicles

    by Ferdous Pervej, Richeng Jin, Huaiyu Dai

    This paper proposes a vehicular edge federated learning (VEFL) solution, where an edge server leverages highly mobile connected vehicles’ (CVs’) onboard central processing units (CPUs) and local datasets to train a global model. Convergence analysis reveals that the VEFL training loss depends on the successful receptions of the CVs’ trained models over the intermittent vehicle-to-infrastructure (V2I) wireless links. Owing to high mobility, in the full device participation case (FDPC), the edge server aggregates client model parameters based on a weighted combination according to the CVs’ dataset sizes and sojourn periods, while it selects a subset of CVs in the partial device participation case (PDPC). We then devise joint VEFL and radio access technology (RAT) parameters optimization problems under delay, energy and cost constraints to maximize the probability of successful reception of the locally trained models. Considering that the optimization problem is NP-hard, we decompose it into a VEFL parameter optimization sub-problem, given the estimated worst-case sojourn period, delay and energy expense, and an online RAT parameter optimization sub-problem. Finally, extensive simulations are conducted to validate the effectiveness of the proposed solutions with a practical 5G new radio (5G-NR) RAT under a realistic microscopic mobility model.