arXiv subjects

Afaf Taik

Publications and source records attributed to Afaf Taik.

13 recordsLinked to original sources

arXiv2025

Fairness in Federated Learning: Fairness for Whom?

Fairness in federated learning has emerged as a rapidly growing area of research, with numerous works proposing formal definitions and algorithmic interventions. Yet, despite this technical progress, fairness in FL is often defined and evaluated in ways that abstract away from the sociotechnical contexts in which these systems are deployed. In this paper, we argue that existing approaches tend to optimize narrow system level metrics, such as performance parity or contribution-based rewards, while overlooking how harms arise throughout the FL lifecycle and how they impact diverse stakeholders. We support this claim through a critical analysis of the literature, based on a systematic annotation of papers for their fairness definitions, design decisions, evaluation practices, and motivating use cases. Our analysis reveals five recurring pitfalls: 1) fairness framed solely through the lens of server client architecture, 2) a mismatch between simulations and motivating use-cases and contexts, 3) definitions that conflate protecting the system with protecting its users, 4) interventions that target isolated stages of the lifecycle while neglecting upstream and downstream effects, 5) and a lack of multi-stakeholder alignment where multiple fairness definitions can be relevant at once. Building on these insights, we propose a harm centered framework that links fairness definitions to concrete risks and stakeholder vulnerabilities. We conclude with recommendations for more holistic, context-aware, and accountable fairness research in FL.

cs.LG↗

arXiv2025

Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects

Conventional AI evaluation approaches concentrated within the AI stack exhibit systemic limitations for exploring, navigating and resolving the human and societal factors that play out in real world deployment such as in education, finance, healthcare, and employment sectors. AI capability evaluations can capture detail about first-order effects, such as whether immediate system outputs are accurate, or contain toxic, biased or stereotypical content, but AI's second-order effects, i.e. any long-term outcomes and consequences that may result from AI use in the real world, have become a significant area of interest as the technology becomes embedded in our daily lives. These secondary effects can include shifts in user behavior, societal, cultural and economic ramifications, workforce transformations, and long-term downstream impacts that may result from a broad and growing set of risks. This position paper argues that measuring the indirect and secondary effects of AI will require expansion beyond static, single-turn approaches conducted in silico to include testing paradigms that can capture what actually materializes when people use AI technology in context. Specifically, we describe the need for data and methods that can facilitate contextual awareness and enable downstream interpretation and decision making about AI's secondary effects, and recommend requirements for a new ecosystem.

cs.CY↗

arXiv2025

Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning

Algorithmic modeling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions. A perspective on this arbitrariness that has recently gained interest is multiplicity-the study of arbitrariness across a set of "good models", i.e., those likely to be deployed in practice. In this work, we systemize the literature on multiplicity by: (a) formalizing the terminology around model design choices and their contribution to arbitrariness, (b) expanding the definition of multiplicity to incorporate underrepresented forms beyond just predictions and explanations, (c) clarifying the distinction between multiplicity and other lenses of arbitrariness, i.e., uncertainty and variance, and (d) distilling the benefits and potential risks of multiplicity into overarching trends, situating it within the broader landscape of responsible AI. We conclude by identifying open research questions and highlighting emerging trends in this young but rapidly growing area of research.

cs.LG↗

arXiv2025

Enhancing Privacy in the Early Detection of Sexual Predators Through Federated Learning and Differential Privacy

The increased screen time and isolation caused by the COVID-19 pandemic have led to a significant surge in cases of online grooming, which is the use of strategies by predators to lure children into sexual exploitation. Previous efforts to detect grooming in industry and academia have involved accessing and monitoring private conversations through centrally-trained models or sending private conversations to a global server. In this work, we implement a privacy-preserving pipeline for the early detection of sexual predators. We leverage federated learning and differential privacy in order to create safer online spaces for children while respecting their privacy. We investigate various privacy-preserving implementations and discuss their benefits and shortcomings. Our extensive evaluation using real-world data proves that privacy and utility can coexist with only a slight reduction in utility.

cs.CL↗

arXiv2024

From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards

Recent progress in large language models (LLMs) has led to their widespread adoption in various domains. However, these advancements have also introduced additional safety risks and raised concerns regarding their detrimental impact on already marginalized populations. Despite growing mitigation efforts to develop safety safeguards, such as supervised safety-oriented fine-tuning and leveraging safe reinforcement learning from human feedback, multiple concerns regarding the safety and ingrained biases in these models remain. Furthermore, previous work has demonstrated that models optimized for safety often display exaggerated safety behaviors, such as a tendency to refrain from responding to certain requests as a precautionary measure. As such, a clear trade-off between the helpfulness and safety of these models has been documented in the literature. In this paper, we further investigate the effectiveness of safety measures by evaluating models on already mitigated biases. Using the case of Llama 2 as an example, we illustrate how LLMs' safety responses can still encode harmful assumptions. To do so, we create a set of non-toxic prompts, which we then use to evaluate Llama models. Through our new taxonomy of LLMs responses to users, we observe that the safety/helpfulness trade-offs are more pronounced for certain demographic groups which can lead to quality-of-service harms for marginalized populations.

cs.LG↗

arXiv2024

Differentially Private Clustered Federated Learning

Federated learning (FL), which is a decentralized machine learning (ML) approach, often incorporates differential privacy (DP) to provide rigorous data privacy guarantees. Previous works attempted to address high structured data heterogeneity in vanilla FL settings through clustering clients (a.k.a clustered FL), but these methods remain sensitive and prone to errors, further exacerbated by the DP noise. This vulnerability makes the previous methods inappropriate for differentially private FL (DPFL) settings with structured data heterogeneity. To address this gap, we propose an algorithm for differentially private clustered FL, which is robust to the DP noise in the system and identifies the underlying clients' clusters correctly. To this end, we propose to cluster clients based on both their model updates and training loss values. Furthermore, for clustering clients' model updates at the end of the first round, our proposed approach addresses the server's uncertainties by employing large batch sizes as well as Gaussian Mixture Models (GMM) to reduce the impact of DP and stochastic noise and avoid potential clustering errors. This idea is efficient especially in privacy-sensitive scenarios with more DP noise. We provide theoretical analysis to justify our approach and evaluate it across diverse data distributions and privacy budgets. Our experimental results show its effectiveness in addressing large structured data heterogeneity in DPFL.

cs.LG↗

arXiv2023

Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements

The growing utilization of machine learning (ML) in decision-making processes raises questions about its benefits to society. In this study, we identify and analyze three axes of heterogeneity that significantly influence the trajectory of ML products. These axes are i) values, culture and regulations, ii) data composition, and iii) resource and infrastructure capacity. We demonstrate how these axes are interdependent and mutually influence one another, emphasizing the need to consider and address them jointly. Unfortunately, the current research landscape falls short in this regard, often failing to adopt a holistic approach. We examine the prevalent practices and methodologies that skew these axes in favor of a selected few, resulting in power concentration, homogenized control, and increased dependency. We discuss how this fragmented study of the three axes poses a significant challenge, leading to an impractical solution space that lacks reflection of real-world scenarios. Addressing these issues is crucial to ensure a more comprehensive understanding of the interconnected nature of society and to foster the democratic and inclusive development of ML systems that are more aligned with real-world complexities and its diverse requirements.

cs.CY↗

arXiv2022

Federated Deep Reinforcement Learning for Open RAN Slicing in 6G Networks

Radio access network (RAN) slicing is a key element in enabling current 5G networks and next-generation networks to meet the requirements of different services in various verticals. However, the heterogeneous nature of these services' requirements, along with the limited RAN resources, makes the RAN slicing very complex. Indeed, the challenge that mobile virtual network operators (MVNOs) face is to rapidly adapt their RAN slicing strategies to the frequent changes of the environment constraints and service requirements. Machine learning techniques, such as deep reinforcement learning (DRL), are increasingly considered a key enabler for automating the management and orchestration of RAN slicing operations. Nerveless, the ability to generalize DRL models to multiple RAN slicing environments may be limited, due to their strong dependence on the environment data on which they are trained. Federated learning enables MVNOs to leverage more diverse training inputs for DRL without the high cost of collecting this data from different RANs. In this paper, we propose a federated deep reinforcement learning approach for RAN slicing. In this approach, MVNOs collaborate to improve the performance of their DRL-based RAN slicing models. Each MVNO trains a DRL model and sends it for aggregation. The aggregated model is then sent back to each MVNO for immediate use and further training. The simulation results show the effectiveness of the proposed DRL approach.

cs.DC↗

arXiv2022

Empowering Prosumer Communities in Smart Grid with Wireless Communications and Federated Edge Learning

The exponential growth of distributed energy resources is enabling the transformation of traditional consumers in the smart grid into prosumers. Such transition presents a promising opportunity for sustainable energy trading. Yet, the integration of prosumers in the energy market imposes new considerations in designing unified and sustainable frameworks for efficient use of the power and communication infrastructure. Furthermore, several issues need to be tackled to adequately promote the adoption of decentralized renewable-oriented systems, such as communication overhead, data privacy, scalability, and sustainability. In this article, we present the different aspects and challenges to be addressed for building efficient energy trading markets in relation to communication and smart decision-making. Accordingly, we propose a multi-level pro-decision framework for prosumer communities to achieve collective goals. Since the individual decisions of prosumers are mainly driven by individual self-sufficiency goals, the framework prioritizes the individual prosumers' decisions and relies on the 5G wireless network for fast coordination among community members. In fact, each prosumer predicts energy production and consumption to make proactive trading decisions as a response to collective-level requests. Moreover, the collaboration of the community is further extended by including the collaborative training of prediction models using Federated Learning, assisted by edge servers and prosumer home-area equipment. In addition to preserving prosumers' privacy, we show through evaluations that training prediction models using Federated Learning yields high accuracy for different energy resources while reducing the communication overhead.

eess.SP↗

arXiv2022

Data-Aware Device Scheduling for Federated Edge Learning

Federated Edge Learning (FEEL) involves the collaborative training of machine learning models among edge devices, with the orchestration of a server in a wireless edge network. Due to frequent model updates, FEEL needs to be adapted to the limited communication bandwidth, scarce energy of edge devices, and the statistical heterogeneity of edge devices' data distributions. Therefore, a careful scheduling of a subset of devices for training and uploading models is necessary. In contrast to previous work in FEEL where the data aspects are under-explored, we consider data properties at the heart of the proposed scheduling algorithm. To this end, we propose a new scheduling scheme for non-independent and-identically-distributed (non-IID) and unbalanced datasets in FEEL. As the data is the key component of the learning, we propose a new set of considerations for data characteristics in wireless scheduling algorithms in FEEL. In fact, the data collected by the devices depends on the local environment and usage pattern. Thus, the datasets vary in size and distributions among the devices. In the proposed algorithm, we consider both data and resource perspectives. In addition to minimizing the completion time of FEEL as well as the transmission energy of the participating devices, the algorithm prioritizes devices with rich and diverse datasets. We first define a general framework for the data-aware scheduling and the main axes and requirements for diversity evaluation. Then, we discuss diversity aspects and some exploitable techniques and metrics. Next, we formulate the problem and present our FEEL scheduling algorithm. Evaluations in different scenarios show that our proposed FEEL scheduling algorithm can help achieve high accuracy in few rounds with a reduced cost.

cs.DC↗

arXiv2022

Clustered Vehicular Federated Learning: Process and Optimization

Federated Learning (FL) is expected to play a prominent role for privacy-preserving machine learning (ML) in autonomous vehicles. FL involves the collaborative training of a single ML model among edge devices on their distributed datasets while keeping data locally. While FL requires less communication compared to classical distributed learning, it remains hard to scale for large models. In vehicular networks, FL must be adapted to the limited communication resources, the mobility of the edge nodes, and the statistical heterogeneity of data distributions. Indeed, a judicious utilization of the communication resources alongside new perceptive learning-oriented methods are vital. To this end, we propose a new architecture for vehicular FL and corresponding learning and scheduling processes. The architecture utilizes vehicular-to-vehicular(V2V) resources to bypass the communication bottleneck where clusters of vehicles train models simultaneously and only the aggregate of each cluster is sent to the multi-access edge (MEC) server. The cluster formation is adapted for single and multi-task learning, and takes into account both communication and learning aspects. We show through simulations that the proposed process is capable of improving the learning accuracy in several non-independent and-identically-distributed (non-i.i.d) and unbalanced datasets distributions, under mobility constraints, in comparison to standard FL.

cs.CE↗

arXiv2022

Electrical Load Forecasting Using Edge Computing and Federated Learning

In the smart grid, huge amounts of consumption data are used to train deep learning models for applications such as load monitoring and demand response. However, these applications raise concerns regarding security and have high accuracy requirements. In one hand, the data used is privacy-sensitive. For instance, the fine-grained data collected by a smart meter at a consumer's home may reveal information on the appliances and thus the consumer's behaviour at home. On the other hand, the deep learning models require big data volumes with enough variety and to be trained adequately. In this paper, we evaluate the use of Edge computing and federated learning, a decentralized machine learning scheme that allows to increase the volume and diversity of data used to train the deep learning models without compromising privacy. This paper reports, to the best of our knowledge, the first use of federated learning for household load forecasting and achieves promising results. The simulations were done using Tensorflow Federated on the data from 200 houses from Texas, USA.

cs.CE↗

arXiv2022

Data-Quality Based Scheduling for Federated Edge Learning

FEderated Edge Learning (FEEL) has emerged as a leading technique for privacy-preserving distributed training in wireless edge networks, where edge devices collaboratively train machine learning (ML) models with the orchestration of a server. However, due to frequent communication, FEEL needs to be adapted to the limited communication bandwidth. Furthermore, the statistical heterogeneity of local datasets' distributions, and the uncertainty about the data quality pose important challenges to the training's convergence. Therefore, a meticulous selection of the participating devices and an analogous bandwidth allocation are necessary. In this paper, we propose a data-quality based scheduling (DQS) algorithm for FEEL. DQS prioritizes reliable devices with rich and diverse datasets. In this paper, we define the different components of the learning algorithm and the data-quality evaluation. Then, we formulate the device selection and the bandwidth allocation problem. Finally, we present our DQS algorithm for FEEL, and we evaluate it in different data poisoning scenarios.

cs.DC↗