Search

Training machine learning models with the only accuracy as a final goal may promote prejudices and discriminatory behaviors embedded in the data. One solution is to learn latent representations that fulfill specific fairness metrics. Different types of learning methods are employed to map data into the fair representational space. The main purpose is to learn a latent representation of data that scores well on a fairness metric while maintaining the usability for the downstream task. In this paper, we propose a new fair representation learning approach that leverages different levels of representation of data to tighten the fairness bounds of the learned representation. Our results show that stacking different auto-encoders and enforcing fairness at different latent spaces result in an improvement of fairness compared to other existing approaches., Comment: ICML2021 ML4data Workshop Paper

Generative adversarial networks (GANs) are one of the greatest advances in AI in recent years. With their ability to directly learn the probability distribution of data, and then sample synthetic realistic data. Many applications have emerged, using GANs to solve classical problems in machine learning, such as data augmentation, class unbalance problems, and fair representation learning. In this paper, we analyze and highlight fairness concerns of GANs model. In this regard, we show empirically that GANs models may inherently prefer certain groups during the training process and therefore they're not able to homogeneously generate data from different groups during the testing phase. Furthermore, we propose solutions to solve this issue by conditioning the GAN model towards samples' group or using ensemble method (boosting) to allow the GAN model to leverage distributed structure of data during the training phase and generate groups at equal rate during the testing phase., Comment: Corrected typos, added results on CelibA dataset

Unmanned aerial vehicles (UAVs) can provide an effective solution for improving the coverage, capacity, and the overall performance of terrestrial wireless cellular networks. In particular, UAV-assisted cellular networks can meet the stringent performance requirements of the fifth generation new radio (5G NR) applications. In this paper, the problem of energy-efficient resource allocation in UAV-assisted cellular networks is studied under the reliability and latency constraints of 5G NR applications. The framework of ruin theory is employed to allow solar-powered UAVs to capture the dynamics of harvested and consumed energies. First, the surplus power of every UAV is modeled, and then it is used to compute the probability of ruin of the UAVs. The probability of ruin denotes the vulnerability of draining out the power of a UAV. Next, the probability of ruin is used for efficient user association with each UAV. Then, power allocation for 5G NR applications is performed to maximize the achievable network rate using the water-filling approach. Simulation results demonstrate that the proposed ruin-based scheme can enhance the flight duration up to 61% and the number of served users in a UAV flight by up to 58\%, compared to a baseline SINR-based scheme.

Recently, the coexistence of ultra-reliable and low-latency communication (URLLC) and enhanced mobile broadband (eMBB) services on the same licensed spectrum has gained a lot of attention from both academia and industry. However, the coexistence of these services is not trivial due to the diverse multiple access protocols, contrasting frame distributions in the existing network, and the distinct quality of service requirements posed by these services. Therefore, such coexistence drives towards a challenging resource scheduling problem. To address this problem, in this paper, we first investigate the possibilities of scheduling URLLC packets in incumbent eMBB traffic. In this regard, we formulate an optimization problem for coexistence by dynamically adopting a superposition or puncturing scheme. In particular, the aim is to provide spectrum access to the URLLC users while reducing the intervention on incumbent eMBB users. Next, we apply the one-to-one matching game to find stable URLLC-eMBB pairs that can coexist on the same spectrum. Then, we apply the contract theory framework to design contracts for URLLC users to adopt the superposition scheme. Simulation results reveal that the proposed contract-based scheduling scheme achieves up to 63% of the eMBB rate for the "No URLLC" case compared to the "Puncturing" scheme., Comment: Submitted to IEEE Access

Recent years have disclosed a remarkable proliferation of compute-intensive applications in smart cities. Such applications continuously generate enormous amounts of data which demand strict latency-aware computational processing capabilities. Although edge computing is an appealing technology to compensate for stringent latency related issues, its deployment engenders new challenges. In this survey, we highlight the role of edge computing in realizing the vision of smart cities. First, we analyze the evolution of edge computing paradigms. Subsequently, we critically review the state-of-the-art literature focusing on edge computing applications in smart cities. Later, we categorize and classify the literature by devising a comprehensive and meticulous taxonomy. Furthermore, we identify and discuss key requirements, and enumerate recently reported synergies of edge computing enabled smart cities. Finally, several indispensable open challenges along with their causes and guidelines are discussed, serving as future research directions.

5G wireless systems will extend mobile communication services beyond mobile telephony, mobile broadband, and massive machine-type communication into new application domains, namely the so-called vertical domains including the smart factory, smart vehicles, smart grid, smart city, etc. Supporting these vertical domains comes with demanding requirements: high-availability, high-reliability, low-latency, and in some cases, high-accuracy positioning. In this survey, we first identify the potential key performance requirements of 5G communication in support of automation in the vertical domains and highlight the 5G enabling technologies conceived for meeting these requirements. We then discuss the key challenges faced both by industry and academia which have to be addressed in order to support automation in the vertical domains. We also provide a survey of the related research dedicated to automation in the vertical domains. Finally, our vision of 6G wireless systems is discussed briefly.

LTE in the unlicensed band (LTE-U) is a promising solution to overcome the scarcity of the wireless spectrum. However, to reap the benefits of LTE-U, it is essential to maintain its effective coexistence with WiFi systems. Such a coexistence, hence, constitutes a major challenge for LTE-U deployment. In this paper, the problem of unlicensed spectrum sharing among WiFi and LTE-U system is studied. In particular, a fair time sharing model based on \emph{ruin theory} is proposed to share redundant spectral resources from the unlicensed band with LTE-U without jeopardizing the performance of the WiFi system. Fairness among both WiFi and LTE-U is maintained by applying the concept of the probability of ruin. In particular, the probability of ruin is used to perform efficient duty-cycle allocation in LTE-U, so as to provide fairness to the WiFi system and maintain certain WiFi performance. Simulation results show that the proposed ruin-based algorithm provides better fairness to the WiFi system as compared to equal duty-cycle sharing among WiFi and LTE-U., Comment: Accepted in IEEE Communications Letters (09-Dec 2018)