Hardware Software Co-design of Statistical and Deep Learning Frameworks for Wideband Sensing on Zynq System on Chip

With the introduction of spectrum sharing and heterogeneous services in next-generation networks, the base stations need to sense the wideband spectrum and identify the spectrum resources to meet the quality-of-service, bandwidth, and latency constraints. Sub-Nyquist sampling (SNS) enables digitization for sparse wideband spectrum without needing Nyquist speed analog-to-digital converters. However, SNS demands additional signal processing algorithms for spectrum reconstruction, such as the well-known orthogonal matching pursuit (OMP) algorithm. OMP is also widely used in other compressed sensing applications. The first contribution of this work is efficiently mapping the OMP algorithm on the Zynq system-on-chip (ZSoC) consisting of an ARM processor and FPGA. Experimental analysis shows a significant degradation in OMP performance for sparse spectrum. Also, OMP needs prior knowledge of spectrum sparsity. We address these challenges via deep-learning-based architectures and efficiently map them on the ZSoC platform as second contribution. Via hardware-software co-design, different versions of the proposed architecture obtained by partitioning between software (ARM processor) and hardware (FPGA) are considered. The resource, power, and execution time comparisons for given memory constraints and a wide range of word lengths are presented for these architectures.

On the Enabling of Multi-user Communications with Reconfigurable Intelligent Surfaces

Reconfigurable Intelligent Surface (RIS) composed of programmable actuators is a promising technology, thanks to its capability in manipulating Electromagnetic (EM) wavefronts. In particular, RISs have the potential to provide significant performance improvements for wireless networks. However, to do so, a proper configuration of the reflection coefficients of the unit cells in the RIS is required. RISs are sophisticated platforms so the design and fabrication complexity might be uneconomical for single-user scenarios while a RIS that can service multi-users justifies the costs. For the first time, we propose an efficient reconfiguration technique providing the multi-beam radiation pattern. Thanks to the analytical model the reconfiguration profile is at hand compared to time-consuming optimization techniques. The outcome can pave the wave for commercial use of multi-user communication beyond 5G networks. We analyze the performance of our proposed RIS technology for indoor and outdoor scenarios, given the broadcast mode of operation. The aforesaid scenarios encompass some of the most challenging scenarios that wireless networks encounter. We show that our proposed technique provisions sufficient gains in the observed channel capacity when the users are close to the RIS in the indoor office environment scenario. Further, we report more than one order of magnitude increase in the system throughput given the outdoor environment. The results prove that RIS with the ability to communicate with multiple users can empower wireless networks with great capacity.

Computing Graph Neural Networks: A Survey from Algorithms to Accelerators

Graph Neural Networks (GNNs) have exploded onto the machine learning scene in recent years owing to their capability to model and learn from graph-structured data. Such an ability has strong implications in a wide variety of fields whose data is inherently relational, for which conventional neural networks do not perform well. Indeed, as recent reviews can attest, research in the area of GNNs has grown rapidly and has lead to the development of a variety of GNN algorithm variants as well as to the exploration of groundbreaking applications in chemistry, neurology, electronics, or communication networks, among others. At the current stage of research, however, the efficient processing of GNNs is still an open challenge for several reasons. Besides of their novelty, GNNs are hard to compute due to their dependence on the input graph, their combination of dense and very sparse operations, or the need to scale to huge graphs in some applications. In this context, this paper aims to make two main contributions. On the one hand, a review of the field of GNNs is presented from the perspective of computing. This includes a brief tutorial on the GNN fundamentals, an overview of the evolution of the field in the last decade, and a summary of operations carried out in the multiple phases of different GNN algorithm variants. On the other hand, an in-depth analysis of current software and hardware acceleration schemes is provided, from which a hardware-software, graph-aware, and communication-centric vision for GNN accelerators is distilled.

Radiation pattern prediction for Metasurfaces: A Neural Network based approach

As the current standardization for the 5G networks nears completion, work towards understanding the potential technologies for the 6G wireless networks is already underway. One of these potential technologies for the 6G networks are Reconfigurable Intelligent Surfaces (RISs). They offer unprecedented degrees of freedom towards engineering the wireless channel, i.e., the ability to modify the characteristics of the channel whenever and however required. Nevertheless, such properties demand that the response of the associated metasurface (MSF) is well understood under all possible operational conditions. While an understanding of the radiation pattern characteristics can be obtained through either analytical models or full wave simulations, they suffer from inaccuracy under certain conditions and extremely high computational complexity, respectively. Hence, in this paper we propose a novel neural networks based approach that enables a fast and accurate characterization of the MSF response. We analyze multiple scenarios and demonstrate the capabilities and utility of the proposed methodology. Concretely, we show that this method is able to learn and predict the parameters governing the reflected wave radiation pattern with an accuracy of a full wave simulation (98.8%-99.8%) and the time and computational complexity of an analytical model. The aforementioned result and methodology will be of specific importance for the design, fault tolerance and maintenance of the thousands of RISs that will be deployed in the 6G network environment.

ManyModalQA: Modality Disambiguation and QA over Diverse Inputs

We present a new multimodal question answering challenge, ManyModalQA, in which an agent must answer a question by considering three distinct modalities: text, images, and tables. We collect our data by scraping Wikipedia and then utilize crowdsourcing to collect question-answer pairs. Our questions are ambiguous, in that the modality that contains the answer is not easily determined based solely upon the question. To demonstrate this ambiguity, we construct a modality selector (or disambiguator) network, and this model gets substantially lower accuracy on our challenge set, compared to existing datasets, indicating that our questions are more ambiguous. By analyzing this model, we investigate which words in the question are indicative of the modality. Next, we construct a simple baseline ManyModalQA model, which, based on the prediction from the modality selector, fires a corresponding pre-trained state-of-the-art unimodal QA model. We focus on providing the community with a new manymodal evaluation set and only provide a fine-tuning set, with the expectation that existing datasets and approaches will be transferred for most of the training, to encourage low-resource generalization without large, monolithic training sets for each new task. There is a significant gap between our baseline models and human performance; therefore, we hope that this challenge encourages research in end-to-end modality disambiguation and multimodal QA models, as well as transfer learning. Code and data available at: https://github.com/hannandarryl/ManyModalQA