OPAC - Pencarian Artikel Jurnal & Majalah Library USD
Menampilkan semua artikel (Halaman 742 dari 34166, Total: 341652 data)
A Comprehensive Survey on Distributed Training of Graph Neural Networks
klik untuk membaca file PDF
| Pengarang | : | - |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 111 (No. 12) |
| Halaman | : | 1572-1606 |
| Abstrak | : | Graph neural networks (GNNs) have been demonstrated to be a powerful algorithmic model in broad application fields for their effectiveness in learning over graphs. To scale GNN training up for large-scale and ever-growing graphs, the most promising solution is distributed training that distributes the workload of training across multiple computing nodes. At present, the volume of related research on distributed GNN training is exceptionally vast, accompanied by an extraordinarily rapid pace of publication. Moreover, the approaches reported in these studies exhibit significant divergence. This situation poses a considerable challenge for newcomers, hindering their ability to grasp a comprehensive understanding of the workflows, computational patterns, communication strategies, and optimization techniques employed in distributed GNN training. As a result, there is a pressing need for a survey to provide correct recognition, analysis, and comparisons in this field. In this article, we provide a comprehensive survey of distributed GNN training by investigating various optimization techniques used in distributed GNN training. First, distributed GNN training is classified into several categories according to their workflows. In addition, their computational patterns and communication patterns, as well as the optimization techniques proposed by recent work, are introduced. Second, the software frameworks and hardware platforms of distributed GNN training are also introduced for a deeper understanding. Third, distributed GNN training is compared with distributed training of deep neural networks (DNNs), emphasizing the uniqueness of distributed GNN training. Finally, interesting issues and opportunities in this field are discussed. |
A Visionary Look at the Security of Reconfigurable Cloud Computing
| Pengarang | : | - |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 111 (No. 12) |
| Halaman | : | 1548-1571 |
| Abstrak | : | Field-programmable gate arrays (FPGAs) have become critical components in many cloud computing platforms. These devices possess the fine-grained parallelism and specialization needed to accelerate applications ranging from machine learning to networking and signal processing, among many others. Unfortunately, fine-grained programmability also makes FPGAs a security risk. Here, we review the current scope of attacks on cloud FPGAs and their remediation. Many of the FPGA security limitations are enabled by the shared power distribution network in FPGA devices. The simultaneous sharing of FPGAs is a particular concern. Other attacks on the memory, host microprocessor, and input/output channels are also possible. After examining current attacks, we describe trends in cloud architecture and how they are likely to impact possible future attacks. FPGA integration into cloud hypervisors and system software will provide extensive computing opportunities but invite new avenues of attack. We identify a series of system, software, and FPGA architectural changes that will facilitate improved security for cloud FPGAs and the overall systems in which they are located. |
Deep-Learning-Based 3-D Surface Reconstruction A Survey
| Pengarang | : | Anis Farshian |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 111 (No. 11) |
| Halaman | : | 1464-1501 |
| Abstrak | : | In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input, is of great interest to a large variety of application fields. DL-based approaches show promising quantitative and qualitative surface reconstruction performance compared to traditional computer vision and geometric algorithms. This survey provides a comprehensive overview of these DL-based methods for 3-D surface reconstruction. To this end, we will first discuss input data modalities, such as volumetric data, point clouds, and RGB, single-view, multiview, and depth images, along with corresponding acquisition technologies and common benchmark datasets. For practical purposes, we also discuss evaluation metrics enabling us to judge the reconstructive performance of different methods. The main part of the document will introduce a methodological taxonomy ranging from point- and mesh-based techniques to volumetric and implicit neural approaches. Recent research trends, both methodological and for applications, are highlighted, pointing toward future developments. |
Zero Shot and Few-Shot Learning With Knowledge Graphs: A Comprehensive Survey
| Pengarang | : | - |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 111 (No. 6) |
| Halaman | : | 653-685 |
| Abstrak | : | Machine learning (ML), especially deep neural networks, has achieved great success, but many of them often rely on a number of labeled samples for supervision. As sufficient labeled training data are not always ready due to, e.g., continuously emerging prediction targets and costly sample annotation in real-world applications, ML with sample shortage is now being widely investigated. Among all these studies, many prefer to utilize auxiliary information including those in the form of knowledge graph (KG) to reduce the reliance on labeled samples. In this survey, we have comprehensively reviewed over 90 articles about KG-aware research for two major sample shortage settings—zero-shot learning (ZSL) where some classes to be predicted have no labeled samples and few-shot learning (FSL) where some classes to be predicted have only a small number of labeled samples that are available. We first introduce KGs used in ZSL and FSL as well as their construction methods and then systematically categorize and summarize KG-aware ZSL and FSL methods, dividing them into different paradigms, such as the mapping-based, the data augmentation, the propagation-based, and the optimization-based. We next present different applications, including not only KG augmented prediction tasks such as image classification, question answering, text classification, and knowledge extraction but also KG completion tasks and some typical evaluation resources for each task. We eventually discuss some challenges and open problems from different perspectives. |
Bottom Up and Top Down Approaches for the Design of Neuromorphic Processing Systems Tradeoffs and Synergies Between Natural and Artificial Intelligence
| Pengarang | : | Danes Jaya Negara |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 111 (No. 6) |
| Halaman | : | 623-652 |
| Abstrak | : | While Moore’s law has driven exponential computing power expectations, its nearing end calls for new avenues for improving the overall system performance. One of these avenues is the exploration of alternative brain-inspired computing architectures that aim at achieving the flexibility and computational efficiency of biological neural processing systems. Within this context, neuromorphic engineering represents a paradigm shift in computing based on the implementation of spiking neural network architectures in which processing and memory are tightly colocated. In this article, we provide a comprehensive overview of the field, highlighting the different levels of granularity at which this paradigm shift is realized and comparing design approaches that focus on replicating natural intelligence (bottom-up) versus those that aim at solving practical artificial intelligence applications (top-down). First, we present the analog, mixed-signal, and digital circuit design styles, identifying the boundary between processing and memory through time multiplexing, in-memory computation, and novel devices. Then, we highlight the key tradeoffs for each of the bottom-up and top-down design approaches, survey their silicon implementations, and carry out detailed comparative analyses to extract design guidelines. Finally, we identify necessary synergies and missing elements required to achieve a competitive advantage for neuromorphic systems over conventional machine-learning accelerators in edge computing applications and outline the key ingredients for a framework toward neuromorphic intelligence. |
Cognitive Dynamic Systems: A Review of Theory, Applications, and Recent Advances
| Pengarang | : | - |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 111 (No. 6) |
| Halaman | : | 575-622 |
| Abstrak | : | The field of cognitive dynamic systems (CDSs) is an emerging area of research, whereby engineering learns from neuroscience. Under this framework, engineering systems are configured in a manner that mimics the human brain and improves the utility and performance of traditional systems. In essence, a CDS builds on Fuster’s paradigm of cognition and is fulfilled with the presence of five cognitive processes: the perception-action cycle, memory, attention, intelligence, and language. When augmented with these processes, a system can be classified as a CDS and is afforded the capabilities of processing information and learning from experience through continued interactions with the environment. Tremendous benefit from adopting the CDS framework has been observed in the literature, especially in the fields of cognitive radio and cognitive radar. More recently, the framework has been extended to other areas, such as control theory, risk control, and the Internet of Things; where the potential for drastic performance improvements has been evident in the literature. This comprehensive article presents a thorough background and exposition of the CDS framework and each field where it has been applied. In addition, we provide a comprehensive review of the recent advancements and related works in each domain by summarizing the key facts relating to the methodologies, findings, and limitations of the surveyed papers. Our novel contributions involve being the first source of centralized information on this topic and forming the foundation for future research efforts by presenting suggestions regarding worthwhile avenues for further investigation. |
Micro/Nano Circuits and Systems Design and Design Automation: Challenges and Opportunities
| Pengarang | : | - |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 111 (No. 6) |
| Halaman | : | 561-574 |
| Abstrak | : | The field of design and design automation of micro-/nano-circuits and systems has played a pivotal role in advancing information technologies that are an inseparable part of all our lives. Without the fundamental principles and tools created in this field, modern-day electronic systems that form the foundations of today's information age would not be a reality. Though the field has achieved tremendous success in the past few decades, it is now facing some unprecedented challenges, stemming from foundational technologies all the way to new applications. Business-as-usual approaches are plateauing. New, fundamental research and innovation are needed to sustain the demanded growth. This paper aims to summarize the key challenges and future research directions in the field of micro/nano circuits and systems design and design automation. |
The Information Age and Naval Command & Control
| Pengarang | : | Hira Jhamtani |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 111 (No. 1) |
| Halaman | : | 113-131 |
| Abstrak | : | This is a condensed version of this article originally prepared for the USNA McMullen Naval History Symposium in 2017 and is a collaboration between David Boslaugh, Peter Marland, and John Vardalas (Stevens Institute of Technology) who have previously written about the postwar development of naval digital systems in their respective countries. |
Accessing From the Sky: A Tutorial on UAV Communications for 5G and Beyond
| Pengarang | : | - |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 107 (No. 12) |
| Halaman | : | 2327-2375 |
| Abstrak | : | Unmanned aerial vehicles (UAVs) have found numerous applications and are expected to bring fertile business opportunities in the next decade. Among various enabling technologies for UAVs, wireless communication is essential and has drawn significantly growing attention in recent years. Compared to the conventional terrestrial communications, UAVs’ communications face new challenges due to their high altitude above the ground and great flexibility of movement in the 3-D space. Several critical issues arise, including the line-of-sight (LoS) dominant UAV-ground channels and induced strong aerial-terrestrial network interference, the distinct communication quality-of-service (QoS) requirements for UAV control messages versus payload data, the stringent constraints imposed by the size, weight, and power (SWAP) limitations of UAVs, as well as the exploitation of the new design degree of freedom (DoF) brought by the highly controllable 3-D UAV mobility. In this article, we give a tutorial overview of the recent advances in UAV communications to address the above issues, with an emphasis on how to integrate UAVs into the forthcoming fifth-generation (5G) and future cellular networks. In particular, we partition our discussion into two promising research and application frameworks of UAV communications, namely UAV-assisted wireless communications and cellular-connected UAVs, where UAVs are integrated into the network as new aerial communication platforms and users, respectively. Furthermore, we point out promising directions for future research. |
Technology Prospects for Data-Intensive Computing
| Pengarang | : | Kerem Akarvardar |
| Nama Majalah/Jurnal | : | Proceedings of the IEEE |
| Volume / Edisi | : | 111 (No. 1) |
| Halaman | : | 92-112 |
| Abstrak | : | For many decades, progress in computing hardware has been closely associated with CMOS logic density, performance, and cost. As such, slowdown in 2-D scaling, frequency saturation in CPUs, and increased cost of design and chip fabrication for advanced technology nodes since the early 2000s have led to concerns about how semiconductor technology may evolve in the future. However, the last two decades have also witnessed a parallel development in the application landscape: the advent of big data and consequent rise of data-intensive computing, using techniques such as machine learning. In this article, we advance the idea that data-intensive computing would further cement semiconductor technology as a foundational technology with multidimensional pathways for growth. Continued progress of semiconductor technology in this new context would require the adoption of a system-centric perspective to holistically harness logic, memory, and packaging resources. After examining the performance metrics for data-intensive computing, we present the historical trends for general-purpose graphics processing unit (GPGPU) as a representative data-intensive computing hardware. Thereon, we estimate the values of the key data-intensive computing parameters for the next decade, and our projections may serve as a precursor for a dedicated technology roadmap. By analyzing the compiled data, we identify and discuss specific opportunities and challenges for data-intensive computing hardware technology. |