Rachid El-Azouzi

Ahmad Dabaja, Rachid El-Azouzi

Federated Learning (FL) has gained significant attention in distributed machine learning by enabling collaborative model training across decentralized system while preserving data privacy. Although extensive research has addressed statistical data heterogeneity, FL still faces several challenges, including high communication and computation overheads and severe device heterogeneity, which require further investigation. Prior work has addressed these issues through sub-model training and partial parameter training. However, such methods often suffer from inconsistent parameter distributions across clients, inaccurate global loss estimation, and increased bias and variance. Guided by our empirical analysis, we propose FedPLT (Federated Learning with Partial Layer Training), an innovative and structured partial parameter training approach that exhibits training behavior similar to full model training while assigning client-specific portions of the model according to their communication and computational capabilities. In addition, we evaluate the performance of FedPLT when combined with optimal client sampling under communication constraints. We show that this integration improves FL performance by reducing sampling variance under the same communication budget. Through extensive experiments, we demonstrate that FedPLT achieves performance comparable to, or even surpassing, that of full-model training (i.e., FedAvg), while requiring significantly fewer trainable parameters per client. Moreover, FedPLT outperforms existing methods in highly heterogeneous environments, effectively adapts to client resource constraints, and reduces the number of straggling clients. In particular, FedPLT reduces the number of trainable parameters by 71%-82% while achieving performance on par with full-model training.

Haoran Zhang, Zejun Gong, Zekai Li et al.

Federated learning (FL) allows edge devices to collaboratively train models without sharing local data. As FL gains popularity, clients may need to train multiple unrelated FL models, but communication constraints limit their ability to train all models simultaneously. While clients could train FL models sequentially, opportunistically having FL clients concurrently train different models -- termed multi-model federated learning (MMFL) -- can reduce the overall training time. Prior work uses simple client-to-model assignments that do not optimize the contribution of each client to each model over the course of its training. Prior work on single-model FL shows that intelligent client selection can greatly accelerate convergence, but naïve extensions to MMFL can violate heterogeneous resource constraints at both the server and the clients. In this work, we develop a novel convergence analysis of MMFL with arbitrary client sampling methods, theoretically demonstrating the strengths and limitations of previous well-established gradient-based methods. Motivated by this analysis, we propose MMFL-LVR, a loss-based sampling method that minimizes training variance while explicitly respecting communication limits at the server and reducing computational costs at the clients. We extend this to MMFL-StaleVR, which incorporates stale updates for improved efficiency and stability, and MMFL-StaleVRE, a lightweight variant suitable for low-overhead deployment. Experiments show our methods improve average accuracy by up to 19.1% over random sampling, with only a 5.4% gap from the theoretical optimum (full client participation).

Zakaria Ye, Rachid El-Azouzi, Tania Jimenez et al.

The main task of HTTP Adaptive Streaming is to adapt video quality dynamically under variable network conditions. This is a key feature for multimedia delivery especially when quality of service cannot be granted network-wide and, e.g., throughput may suffer short term fluctuations. Hence, robust bitrate adaptation schemes become crucial in order to improve video quality. The objective, in this context, is to control the filling level of the playback buffer and maximize the quality of the video, while avoiding unnecessary video quality variations. In this paper we study bitrate adaptation algorithms based on Backward-Shifted Coding (BSC), a scalable video coding scheme able to greatly improve video quality. We design bitrate adaptation algorithms that balance video rate smoothness and high network capacity utilization, leveraging both on throughput-based and buffer-based adaptation mechanisms. Extensive simulations using synthetic and real-world video traffic traces show that the proposed scheme performs remarkably well even under challenging network conditions.

Zakaria Ye, Rachid El-Azouzi, Tania Jimenez et al.

Although HTTP-based video streaming can easily penetrate firewalls and profit from Web caches, the underlying TCP may introduce large delays in case of a sudden capacity loss. To avoid an interruption of the video stream in such cases we propose the Backward-Shifted Coding (BSC). Based on Scalable Video Coding (SVC), BSC adds a time-shifted layer of redundancy to the video stream such that future frames are downloaded at any instant. This pre-fetched content maintains a fluent video stream even under highly variant network conditions and leads to high Quality of Experience (QoE). We characterize this QoE gain by analyzing initial buffering time, re-buffering time and content resolution using the Ballot theorem. The probability generating functions of the playback interruption and of the initial buffering latency are provided in closed form. We further compute the quasi-stationary distribution of the video quality, in order to compute the average quality, as well as temporal variability in video quality. Employing these analytic results to optimize QoE shows interesting trade-offs and video streaming at outstanding fluency.

Imen Triki, Rachid El-Azouzi, Majed Haddad

The knowledge of future throughput variations in mobile networks becomes more and more possible today thanks to the rich contextual information provided by mobile applications and services and smartphone sensors. It is even likely that such contextual information, which may include traffic, mobility and radio conditions will lead to a novel agile resource management not yet thought of. In this paper, we propose an framework (called NEWCAST) that anticipates the throughput variations to deliver video streaming content. We develop an optimization problem that realizes a fundamental trade-off among critical metrics that impact the user's perceptual quality of experience (QoE) and the cost of system utilization. Both simulated and real-world throughput traces collected from [1], were carried out to evaluate the performance of NEWCAST. In particular, we show from our numerical results that NEWCAST provides the efficiency that the new 5G architectures require in terms of computational complexity and robustness. We also implement a prototype system of NEWCAST and evaluate it in a real environment with a real player to show its efficiency and scalability compared to baseline adaptive bitrate algorithms.