Israat Haque

Zichong Wang, Nripsuta Saxena, Tongjia Yu et al.

Bias in machine learning has rightly received significant attention over the last decade. However, most fair machine learning (fair-ML) work to address bias in decision-making systems has focused solely on the offline setting. Despite the wide prevalence of online systems in the real world, work on identifying and correcting bias in the online setting is severely lacking. The unique challenges of the online environment make addressing bias more difficult than in the offline setting. First, Streaming Machine Learning (SML) algorithms must deal with the constantly evolving real-time data stream. Second, they need to adapt to changing data distributions (concept drift) to make accurate predictions on new incoming data. Adding fairness constraints to this already complicated task is not straightforward. In this work, we focus on the challenges of achieving fairness in biased data streams while accounting for the presence of concept drift, accessing one sample at a time. We present Fair Sampling over Stream ($FS^2$), a novel fair rebalancing approach capable of being integrated with SML classification algorithms. Furthermore, we devise the first unified performance-fairness metric, Fairness Bonded Utility (FBU), to evaluate and compare the trade-off between performance and fairness of different bias mitigation methods efficiently. FBU simplifies the comparison of fairness-performance trade-offs of multiple techniques through one unified and intuitive evaluation, allowing model designers to easily choose a technique. Overall, extensive evaluations show our measures surpass those of other fair online techniques previously reported in the literature.

Zichong Wang, Yang Zhou, Israat Haque et al.

The increasing use of Machine Learning (ML) software can lead to unfair and unethical decisions, thus fairness bugs in software are becoming a growing concern. Addressing these fairness bugs often involves sacrificing ML performance, such as accuracy. To address this issue, we present a novel counterfactual approach that uses counterfactual thinking to tackle the root causes of bias in ML software. In addition, our approach combines models optimized for both performance and fairness, resulting in an optimal solution in both aspects. We conducted a thorough evaluation of our approach on 10 benchmark tasks using a combination of 5 performance metrics, 3 fairness metrics, and 15 measurement scenarios, all applied to 8 real-world datasets. The conducted extensive evaluations show that the proposed method significantly improves the fairness of ML software while maintaining competitive performance, outperforming state-of-the-art solutions in 84.6% of overall cases based on a recent benchmarking tool.

Kazi Hasan, Thomas Trappenberg, Israat Haque

Radio link failure (RLF) prediction system in Radio Access Networks (RANs) is critical for ensuring seamless communication and meeting the stringent requirements of high data rates, low latency, and improved reliability in 5G networks. However, weather conditions such as precipitation, humidity, temperature, and wind impact these communication links. Usually, historical radio link Key Performance Indicators (KPIs) and their surrounding weather station observations are utilized for building learning-based RLF prediction models. However, such models must be capable of learning the spatial weather context in a dynamic RAN and effectively encoding time series KPIs with the weather observation data. Existing works fail to incorporate both of these essential design aspects of the prediction models. This paper fills the gap by proposing GenTrap, a novel RLF prediction framework that introduces a graph neural network (GNN)-based learnable weather effect aggregation module and employs state-of-the-art time series transformer as the temporal feature extractor for radio link failure prediction. The proposed aggregation method of GenTrap can be integrated into any existing prediction model to achieve better performance and generalizability. We evaluate GenTrap on two real-world datasets (rural and urban) with 2.6 million KPI data points and show that GenTrap offers a significantly higher F1-score (0.93 for rural and 0.79 for urban) compared to its counterparts while possessing generalization capability.

Quazi Mishkatul Alam, Israat Haque, Nael Abu-Ghazaleh

Video analytics are often performed as cloud services in edge settings, mainly to offload computation, and also in situations where the results are not directly consumed at the video sensors. Sending high-quality video data from the edge devices can be expensive both in terms of bandwidth and power use. In order to build a streaming video analytics pipeline that makes efficient use of these resources, it is therefore imperative to reduce the size of the video stream. Traditional video compression algorithms are unaware of the semantics of the video, and can be both inefficient and harmful for the analytics performance. In this paper, we introduce LtC, a collaborative framework between the video source and the analytics server, that efficiently learns to reduce the video streams within an analytics pipeline. Specifically, LtC uses the full-fledged analytics algorithm at the server as a teacher to train a lightweight student neural network, which is then deployed at the video source. The student network is trained to comprehend the semantic significance of various regions within the videos, which is used to differentially preserve the crucial regions in high quality while the remaining regions undergo aggressive compression. Furthermore, LtC also incorporates a novel temporal filtering algorithm based on feature-differencing to omit transmitting frames that do not contribute new information. Overall, LtC is able to use 28-35% less bandwidth and has up to 45% shorter response delay compared to recently published state of the art streaming frameworks while achieving similar analytics performance.

Conrado Boeira, Eduardo Baena, Andrea Lacava et al.

Despite recommendations to deploy real-time Open Radio Access Network (O-RAN) applications (dApps) in containerized environments, existing approaches predominantly rely on bare-metal servers. Moreover, current dApp deployments offer limited visibility into the resource usage patterns of both intelligent and non-intelligent dApps, hindering informed deployment decisions. This work addresses these gaps by implementing and evaluating representative dApps across multiple deployment scenarios (bare-metal and containers) to characterize the trade-offs in latency, scalability, and resource utilization. Additionally, we identify key performance bottlenecks and demonstrate how offloading dApps to emerging hardware accelerators, such as smart Network Interface Cards (NICs), can alleviate these limitations and improve real-time responsiveness in O-RAN systems.

Antor Hasan, Conrado Boeira, Khaleda Papry et al.

The emergence of 5G technology marks a significant milestone in developing telecommunication networks, enabling exciting new applications such as augmented reality and self-driving vehicles. However, these improvements bring an increased management complexity and a special concern in dealing with failures, as the applications 5G intends to support heavily rely on high network performance and low latency. Thus, automatic self-healing solutions have become effective in dealing with this requirement, allowing a learning-based system to automatically detect anomalies and perform Root Cause Analysis (RCA). However, there are inherent challenges to the implementation of such intelligent systems. First, there is a lack of suitable data for anomaly detection and RCA, as labelled data for failure scenarios is uncommon. Secondly, current intelligent solutions are tailored to LTE networks and do not fully capture the spatio-temporal characteristics present in the data. Considering this, we utilize a calibrated simulator, Simu5G, and generate open-source data for normal and failure scenarios. Using this data, we propose Simba, a state-of-the-art approach for anomaly detection and root cause analysis in 5G Radio Access Networks (RANs). We leverage Graph Neural Networks to capture spatial relationships while a Transformer model is used to learn the temporal dependencies of the data. We implement a prototype of Simba and evaluate it over multiple failures. The outcomes are compared against existing solutions to confirm the superiority of Simba.

Md. Monzurul Amin Ifath, Israat Haque

Large language models (LLMs) are increasingly used in applications forming multi-request workflows like document summarization, search-based copilots, and multi-agent programming. While these workflows unlock richer functionality, they also amplify latency and energy demand during inference. Existing measurement and benchmarking efforts either focus on assessing LLM inference systems or consider single-request evaluations, overlooking workflow dependencies and cross-request interactions unique to multi-request workflows. Moreover, the energy usage of such interdependent LLM calls remains underexplored. To address these gaps, this paper presents the first systematic characterization of performance-energy trade-offs in multi-request LLM inference. We develop four representative workloads capturing sequential, interactive, agentic, and composite patterns common in modern deployments. Using an NVIDIA A100 testbed with state-of-the-art serving systems (vLLM and Parrot), we analyze how key energy knobs affect latency, throughput, and component-level energy use. Our findings reveal batch size as the most impactful lever, though benefits are workload dependent. While optimal batching benefits workloads with large shared prompts, it is ineffective for sequential summarization and only partially effective for multi-agent coding. GPU power capping provides modest but predictable savings, while output length induces linear energy scaling with limited efficiency gains. We further show that engine-level optimizations in vLLM maintain higher GPU utilization and efficiency, especially for decode-heavy workloads, while Parrot's workflow-aware scheduling achieves lower energy consumption under strict power constraints. These findings offer actionable guidelines for developers and system operators designing performance- and energy-aware LLM serving systems in emerging multi-request workflows.

Ghazal Sobhani, Md. Monzurul Amin Ifath, Tushar Sharma et al.

The proliferation of the Internet of Things (IoT) and its cutting-edge AI-enabled applications (e.g., autonomous vehicles and smart industries) combine two paradigms: data-driven systems and their deployment on the edge. Usually, edge devices perform inferences to support latency-critical applications. In addition to the performance of these resource-constrained edge devices, their energy usage is a critical factor in adopting and deploying edge applications. Examples of such devices include Raspberry Pi (RPi), Intel Neural Compute Stick (INCS), NVIDIA Jetson nano (NJn), and Google Coral USB (GCU). Despite their adoption in edge deployment for AI inferences, there is no study on their performance and energy usage for informed decision-making on the device and model selection to meet the demands of applications. This study fills the gap by rigorously characterizing the performance of traditional, neural networks, and large language models on the above-edge devices. Specifically, we analyze trade-offs among model F1 score, inference time, inference power, and memory usage. Hardware and framework optimization, along with external parameter tuning of AI models, can balance between model performance and resource usage to realize practical edge AI deployments.

Chengyan Jiang, Jiamin Fan, Talal Halabi et al.

The widespread adoption of smartphones and smart wearable devices has led to the widespread use of Centralized Federated Learning (CFL) for training powerful machine learning models while preserving data privacy. However, CFL faces limitations due to its overreliance on a central server, which impacts latency and system robustness. Decentralized Federated Learning (DFL) is introduced to address these challenges. It facilitates direct collaboration among participating devices without relying on a central server. Each device can independently connect with other devices and share model parameters. This work explores crucial factors influencing the convergence and generalization capacity of DFL models, emphasizing network topologies, non-IID data distribution, and training strategies. We first derive the convergence rate of different DFL model deployment strategies. Then, we comprehensively analyze various network topologies (e.g., linear, ring, star, and mesh) with different degrees of non-IID data and evaluate them over widely adopted machine learning models (e.g., classical, deep neural networks, and Large Language Models) and real-world datasets. The results reveal that models converge to the optimal one for IID data. However, the convergence rate is inversely proportional to the degree of non-IID data distribution. Our findings will serve as valuable guidelines for designing effective DFL model deployments in practical applications.