The communication and networking field is hungry for machine learning decision-making solutions to replace the traditional model-driven approaches that proved to be not rich enough for seizing the ever-growing complexity and heterogeneity of the modern systems in the field. Traditional machine learning solutions assume the existence of (cloud-based) central entities that are in charge of processing the data. Nonetheless, the difficulty of accessing private data, together with the high cost of transmitting raw data to the central entity gave rise to a decentralized machine learning approach called Federated Learning. The main idea of federated learning is to perform an on-device collaborative training of a single machine learning model without having to share the raw training data with any third-party entity. Although few survey articles on federated learning already exist in the literature, the motivation of this survey stems from three essential observations. The first one is the lack of a fine-grained multi-level classification of the federated learning literature, where the existing surveys base their classification on only one criterion or aspect. The second observation is that the existing surveys focus only on some common challenges, but disregard other essential aspects such as reliable client selection, resource management and training service pricing. The third observation is the lack of explicit and straightforward directives for researchers to help them design future federated learning solutions that overcome the state-of-the-art research gaps. To address these points, we first provide a comprehensive tutorial on federated learning and its associated concepts, technologies and learning approaches. We then survey and highlight the applications and future directions of federated learning in the domain of communication and networking. Thereafter, we design a three-level classification scheme that first categorizes the federated learning literature based on the high-level challenge that they tackle. Then, we classify each high-level challenge into a set of specific low-level challenges to foster a better understanding of the topic. Finally, we provide, within each low-level challenge, a fine-grained classification based on the technique used to address this particular challenge. For each category of high-level challenges, we provide a set of desirable criteria and future research directions that are aimed to help the research community design innovative and efficient future solutions. To the best of our knowledge, our survey is the most comprehensive in terms of challenges and techniques it covers and the most fine-grained in terms of the multi-level classification scheme it presents.
Key Points• Somatic CDKN1B (p27) mutations were identified in 16% (13/81) of HCL patients and coexist with BRAFV600E mutations.• CDKN1B is the second most common mutated gene in HCL implicating altered cell cycle regulation and/or senescence in HCL.Hairy cell leukemia (HCL) is marked by near 100% mutational frequency of BRAFV600E mutations. Recurrent cooperating genetic events that may contribute to HCL pathogenesis or affect the clinical course of HCL are currently not described. Therefore, we performed whole exome sequencing to explore the mutational landscape of purine analog refractory HCL. In addition to the disease-defining BRAFV600E mutations, we identified mutations in EZH2, ARID1A, and recurrent inactivating mutations of the cell cycle inhibitor CDKN1B (p27). Targeted deep sequencing of CDKN1B in a larger cohort of HCL patients identify deleterious CDKN1B mutations in 16% of patients with HCL (n 5 13 of 81). In 11 of 13 patients the CDKN1B mutation was clonal, implying an early role of CDKN1B mutations in the pathogenesis of HCL. CDKN1B mutations were not found to impact clinical characteristics or outcome in this cohort. These data identify HCL as having the highest frequency of CDKN1B mutations among cancers and identify CDNK1B as the second most common mutated gene in HCL. Moreover, given the known function of CDNK1B, these data suggest a novel role for alterations in regulation of cell cycle and senescence in HCL with CDKN1B mutations. (Blood. 2015;126(8):1005-1008)
IntroductionHairy-cell leukemia (HCL) is a rare, mature B-cell malignancy presenting with slow progressing pancytopenia and splenomegaly. Classical HCL is successfully treated with chemotherapy, but eradication of minimal residual disease is rarely achieved. 1 Standard treatment fails in a minority of patients, with a potentially fatal outcome.Gain-of-function mutations of the BRAF serine/threonine protein kinase (BRAFV600E) have been identified in nearly all cases of classical HCL, and mitogen-activated protein kinase signaling is considered the key oncogenic pathway in HCL.2 Chung et al 3 recently identified hematopoietic stem cells as the cell of origin of HCL by demonstrating that hematopoietic stem cells, and subsequently cells along the hematopoietic hierarchy, contain mutated BRAF. Currently, however, no other recurrently mutated genes are known to coexist with BRAFV600E mutations in HCL. It is unclear if BRAFV600E mutations alone are sufficient to induce HCL. Moreover, it is also not known if additional mutations may be acquired in BRAFV600E-mutant HCL cells, resulting in acquired resistance to therapies commonly administered to patients with HCL such as purine analogs. Therefore, we performed whole-exome sequencing (WES) in 3 HCL patients who were refractory to purine analog treatment and received the BRAF inhibitor (BRAFi) vemurafenib followed by recurrence testing of novel mutations in a larger cohort of HCL patients.
Study designClinical samples were provided by
Summary
Cloud computing is undeniably becoming the main computing and storage platform for today's major workloads. From Internet of things and Industry 4.0 workloads to big data analytics and decision‐making jobs, cloud systems daily receive a massive number of tasks that need to be simultaneously and efficiently mapped onto the cloud resources. Therefore, deriving an appropriate task scheduling mechanism that can both minimize tasks' execution delay and cloud resources utilization is of prime importance. Recently, the concept of cloud automation has emerged to reduce the manual intervention and improve the resource management in large‐scale cloud computing workloads. In this article, we capitalize on this concept and propose four deep and reinforcement learning‐based scheduling approaches to automate the process of scheduling large‐scale workloads onto cloud computing resources, while reducing both the resource consumption and task waiting time. These approaches are: reinforcement learning (RL), deep Q networks, recurrent neural network long short‐term memory (RNN‐LSTM), and deep reinforcement learning combined with LSTM (DRL‐LSTM). Experiments conducted using real‐world datasets from Google Cloud Platform revealed that DRL‐LSTM outperforms the other three approaches. The experiments also showed that DRL‐LSTM minimizes the CPU usage cost up to 67% compared with the shortest job first (SJF), and up to 35% compared with both the round robin (RR) and improved particle swarm optimization (PSO) approaches. Moreover, our DRL‐LSTM solution decreases the RAM memory usage cost up to 72% compared with the SJF, up to 65% compared with the RR, and up to 31.25% compared with the improved PSO.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.