Machine teaching often involves the creation of an optimal (typically minimal) dataset to help a model (referred to as the `student') achieve specific goals given by a teacher. While abundant in the continuous domain, the studies on the effectiveness of machine teaching in the discrete domain are relatively limited. This paper focuses on machine teaching in the discrete domain, specifically on manipulating student models' predictions based on the goals of teachers via changing the training data efficiently. We formulate this task as a combinatorial optimization problem and solve it by proposing an iterative searching algorithm. Our algorithm demonstrates significant numerical merit in the scenarios where a teacher attempts at correcting erroneous predictions to improve the student's models, or maliciously manipulating the model to misclassify some specific samples to the target class aligned with his personal profits. Experimental results show that our proposed algorithm can have superior performance in effectively and efficiently manipulating the predictions of the model, surpassing conventional baselines.
Extended reality (XR) applications often perform resource-intensive tasks, which are computed remotely, a process that prioritizes the latency criticality aspect. To this end, this paper shows that through leveraging the power of the central cloud (CC), the close proximity of edge computers (ECs), and the flexibility of uncrewed aerial vehicles (UAVs), a UAV-aided hybrid cloud/mobile-edge computing architecture promises to handle the intricate requirements of future XR applications. In this context, this paper distinguishes between two types of XR devices, namely, strong and weak devices. The paper then introduces a cooperative non-orthogonal multiple access (Co-NOMA) scheme, pairing strong and weak devices, so as to aid the XR devices quality-of-user experience by intelligently selecting either the direct or the relay links toward the weak XR devices. A sum logarithmic-rate maximization problem is, thus, formulated so as to jointly determine the computation and communication resources, and link-selection strategy as a means to strike a trade-off between the system throughput and fairness. Subject to realistic network constraints, e.g., power consumption and delay, the optimization problem is then solved iteratively via discrete relaxations, successive-convex approximation, and fractional programming, an approach which can be implemented in a distributed fashion across the network. Simulation results validate the proposed algorithms performance in terms of log-rate maximization, delay-sensitivity, scalability, and runtime performance. The practical distributed Co-NOMA implementation is particularly shown to offer appreciable benefits over traditional multiple access and NOMA methods, highlighting its applicability in decentralized XR systems.
Unmanned aerial vehicles (UAVs) mobility enables flexible and customized federated learning (FL) at the network edge. However, the underlying uncertainties in the aerial-terrestrial wireless channel may lead to a biased FL model. In particular, the distribution of the global model and the aggregation of the local updates within the FL learning rounds at the UAVs are governed by the reliability of the wireless channel. This creates an undesirable bias towards the training data of ground devices with better channel conditions, and vice versa. This paper characterizes the global bias problem of aerial FL in large-scale UAV networks. To this end, the paper proposes a channel-aware distribution and aggregation scheme to enforce equal contribution from all devices in the FL training as a means to resolve the global bias problem. We demonstrate the convergence of the proposed method by experimenting with the MNIST dataset and show its superiority compared to existing methods. The obtained results enable system parameter tuning to relieve the impact of the aerial channel deficiency on the FL convergence rate.
The evolvement of wireless communication services concurs with significant growth in data traffic, thereby inflicting stringent requirements on terrestrial networks. This work invigorates a novel connectivity solution that integrates aerial and terrestrial communications with a cloud-enabled high-altitude platform station (HAPS) to promote an equitable connectivity landscape. Consider a cloud-enabled HAPS connected to both terrestrial base-stations and hot-air balloons via a data-sharing fronthauling strategy. The paper then assumes that both the terrestrial base-stations and the hot-air balloons are grouped into disjoint clusters to serve the aerial and terrestrial users in a coordinated fashion. The work then focuses on finding the user-to-transmitter scheduling and the associated beamforming policies in the downlink direction of cloud-enabled HAPS systems by maximizing two different objectives, namely, the sum-rate and sum-of-log of the long-term average rate, both subject to limited transmit power and finite fronthaul capacity. The paper proposes solving the two non-convex discrete and continuous optimization problems using numerical iterative optimization algorithms. The proposed algorithms rely on well-chosen convexification and approximation steps, namely, fractional programming and sparse beamforming via re-weighted $\ell_0$-norm approximation. The numerical results outline the yielded gain illustrated through equitable access service in crowded and unserved areas, and showcase the numerical benefits stemming from the proposed cloud-enabled HAPS coordination of hot-air balloons and terrestrial base-stations for democratizing connectivity and empowering the digital inclusion framework.
Integrated space-air-ground networks promise to offer a valuable solution space for empowering the sixth generation of communication networks (6G), particularly in the context of connecting the unconnected and ultraconnecting the connected. Such digital inclusion thrive makes resource management problems, especially those accounting for load-balancing considerations, of particular interest. The conventional model-based optimization methods, however, often fail to meet the real-time processing and quality-of-service needs, due to the high heterogeneity of the space-air-ground networks, and the typical complexity of the classical algorithms. Given the premises of artificial intelligence at automating wireless networks design, this paper focuses on showcasing the prospects of machine learning in the context of user scheduling in integrated space-air-ground communications. The paper first overviews the most relevant state-of-the art in the context of machine learning applications to the resource allocation problems, with a dedicated attention to space-air-ground networks. The paper then proposes, and shows the benefit of, one specific application that uses ensembling deep neural networks for optimizing the user scheduling policies in integrated space-high altitude platform station (HAPS)-ground networks. Finally, the paper sheds light on the challenges and open issues that promise to spur the integration of machine learning in space-air-ground networks, namely, online HAPS power adaptation, learning-based channel sensing, data-driven multi-HAPSs resource management, and intelligent flying taxis-empowered systems.
Unlike its intercept, a linear classifier's weight vector cannot be tuned by a simple grid search. Hence, this paper proposes weight vector tuning of a generic binary linear classifier through the parameterization of a decomposition of the discriminant by a scalar which controls the trade-off between conflicting informative and noisy terms. By varying this parameter, the original weight vector is modified in a meaningful way. Applying this method to a number of linear classifiers under a variety of data dimensionality and sample size settings reveals that the classification performance loss due to non-optimal native hyperparameters can be compensated for by weight vector tuning. This yields computational savings as the proposed tuning method reduces to tuning a scalar compared to tuning the native hyperparameter, which may involve repeated weight vector generation along with its burden of optimization, dimensionality reduction, etc., depending on the classifier. It is also found that weight vector tuning significantly improves the performance of Linear Discriminant Analysis (LDA) under high estimation noise. Proceeding from this second finding, an asymptotic study of the misclassification probability of the parameterized LDA classifier in the growth regime where the data dimensionality and sample size are comparable is conducted. Using random matrix theory, the misclassification probability is shown to converge to a quantity that is a function of the true statistics of the data. Additionally, an estimator of the misclassification probability is derived. Finally, computationally efficient tuning of the parameter using this estimator is demonstrated on real data.
Service providers are considering the use of unmanned aerial vehicles (UAVs) to enhance wireless connectivity of cellular networks. To provide connectivity, UAVs have to be backhauled through terrestrial base stations (BSs) to the core network. In particular, we consider millimeter-wave (mmWave) backhauling in the downlink of a hybrid aerial-terrestrial network, where the backhaul links are subject to beamforming misalignment errors. In the proposed model, the user equipment (UE) can connect to either a ground BS or a UAV, where we differentiate between two transmission schemes according to the backhaul status. In one scheme, the UEs are served by the UAVs regardless of whether the backhaul links are good or not. In the other scheme, the UAVs are aware of the backhaul links status, and hence, only the subset of successfully backhauled UAVs can serve the UEs. Using stochastic geometry, the performance of the proposed model is assessed in terms of coverage probability and validated against Monte-Carlo simulations. Several insights are provided for determining some system parameters including the UAVs altitude and required number and the beamforming misalignment error of the backhaul link. The obtained results highlight the impact of the UAVs backhaul link on the UE experience.
Following the recent progress in Terahertz (THz) signal generation and radiation methods, joint THz communications and sensing applications are shaping the future of wireless systems. Towards this end, THz spectroscopy is expected to be carried over user equipment devices to identify material and gaseous components of interest. THz-specific signal processing techniques should complement this re-surged interest in THz sensing for efficient utilization of the THz band. In this paper, we present an overview of these techniques, with an emphasis on signal pre-processing (standard normal variate normalization, min-max normalization, and Savitzky-Golay filtering), feature extraction (principal component analysis, partial least squares, t-distributed stochastic neighbor embedding, and nonnegative matrix factorization), and classification techniques (support vector machines, k-nearest neighbor, discriminant analysis, and naive Bayes). We also address the effectiveness of deep learning techniques by exploring their promising sensing capabilities at the THz band. Lastly, we investigate the performance and complexity trade-offs of the studied methods in the context of joint communications and sensing; we motivate the corresponding use-cases, and we present few future research directions in the field.
Datasets from the fields of bioinformatics, chemometrics, and face recognition are typically characterized by small samples of high-dimensional data. Among the many variants of linear discriminant analysis that have been proposed in order to rectify the issues associated with classification in such a setting, the classifier in [1], composed of an ensemble of randomly projected linear discriminants, seems especially promising; it is computationally efficient and, with the optimal projection dimension parameter setting, is competitive with the state-of-the-art. In this work, we seek to further understand the behavior of this classifier through asymptotic analysis. Under the assumption of a growth regime in which the dataset and projection dimensions grow at constant rates to each other, we use random matrix theory to derive asymptotic misclassification probabilities showing the effect of the ensemble as a regularization of the data sample covariance matrix. The asymptotic errors further help to identify situations in which the ensemble offers a performance advantage. We also develop a consistent estimator of the misclassification probability as an alternative to the computationally-costly cross-validation estimator, which is conventionally used for parameter tuning. Finally, we demonstrate the use of our estimator for tuning the projection dimension on both real and synthetic data.