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.

Weizhao Tang, Rachid El-Azouzi, Cheng Han Lee et al.

Automated marker makers (AMMs) are a class of decentralized exchanges that enable the automated trading of digital assets. They accept deposits of digital tokens from liquidity providers (LPs); tokens can be used by traders to execute trades, which generate fees for the investing LPs. The distinguishing feature of AMMs is that trade prices are determined algorithmically, unlike classical limit order books. Concentrated liquidity market makers (CLMMs) are a major class of AMMs that offer liquidity providers flexibility to decide not only \emph{how much} liquidity to provide, but \emph{in what ranges of prices} they want the liquidity to be used. This flexibility can complicate strategic planning, since fee rewards are shared among LPs. We formulate and analyze a game theoretic model to study the incentives of LPs in CLMMs. Our main results show that while our original formulation admits multiple Nash equilibria and has complexity quadratic in the number of price ticks in the contract, it can be reduced to a game with a unique Nash equilibrium whose complexity is only linear. We further show that the Nash equilibrium of this simplified game follows a waterfilling strategy, in which low-budget LPs use up their full budget, but rich LPs do not. Finally, by fitting our game model to real-world CLMMs, we observe that in liquidity pools with risky assets, LPs adopt investment strategies far from the Nash equilibrium. Under price uncertainty, they generally invest in fewer and wider price ranges than our analysis suggests, with lower-frequency liquidity updates. We show that across several pools, by updating their strategy to more closely match the Nash equilibrium of our game, LPs can improve their median daily returns by \$116, which corresponds to an increase of 0.009\% in median daily return on investment.

Anne Reulke, Mikaël Touati, Rachid El-Azouzi

Addressing infeasibility in non-cooperative games has become an important topic, as many problems across different applications face this issue. In this paper, we propose a new solution concept for generalized games with possibly infeasible individual constraints. A solution is defined as the limit of a sequence of generalized Nash equilibria induced by games with penalty terms relaxing the individual constraints. Existence is established for a broad range of games and we provide conditions allowing to characterize a $ψ$-penalized solution as a strategy profile maximizing every player's utility over all her penalty minimizing strategies. A variation of Divide-the-Dollar serves as an illustrative example. We further establish the compatibility with the GNE and the solution to the Nash bargaining.

Khaoula Otmani, Rachid Elazouzi, Vincent Labatut

In Federated Learning (FL), several clients jointly learn a machine learning model: each client maintains a local model for its local learning dataset, while a master server maintains a global model by aggregating the local models of the client devices. However, the repetitive communication between server and clients leaves room for attacks aimed at compromising the integrity of the global model, causing errors in its targeted predictions. In response to such threats on FL, various defense measures have been proposed in the literature. In this paper, we present a powerful defense against malicious clients in FL, called FedSV, using the Shapley Value (SV), which has been proposed recently to measure user contribution in FL by computing the marginal increase of average accuracy of the model due to the addition of local data of a user. Our approach makes the identification of malicious clients more robust, since during the learning phase, it estimates the contribution of each client according to the different groups to which the target client belongs. FedSV's effectiveness is demonstrated by extensive experiments on MNIST datasets in a cross-silo context under various attacks.

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).

Imen Triki, Quanyan Zhu, Rachid Elazouzi et al.

The quality of experience (QoE) is known to be subjective and context-dependent. Identifying and calculating the factors that affect QoE is indeed a difficult task. Recently, a lot of effort has been devoted to estimate the users QoE in order to improve video delivery. In the literature, most of the QoE-driven optimization schemes that realize trade-offs among different quality metrics have been addressed under the assumption of homogenous populations. Nevertheless, people perceptions on a given video quality may not be the same, which makes the QoE optimization harder. This paper aims at taking a step further in order to address this limitation and meet users profiles. To do so, we propose a closed-loop control framework based on the users(subjective) feedbacks to learn the QoE function and optimize it at the same time. Our simulation results show that our system converges to a steady state, where the resulting QoE function noticeably improves the users feedbacks.

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.