检索结果-内蒙古大学图书馆

Deep Isolation Forest for Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Hongzuo Pang, Guansong Wang, Yijie Wang, Yongjun The College of Computer National University of Defense Technology Changsha410073 China The Science and Technology on Parallel and Distributed Processing Laboratory China The School of Computing and Information Systems Singapore Management University 178902 Singapore

Isolation forest (iForest) has been emerging as arguably the most popular anomaly detector in recent years due to its general effectiveness across different benchmarks and strong scalability. Nevertheless, its linear axis-parallel isolation method often leads to (i) failure in detecting hard anomalies that are difficult to isolate in high-dimensional/non-linear-separable data space, and (ii) notorious algorithmic bias that assigns unexpectedly lower anomaly scores to artefact regions. These issues contribute to high false negative errors. Several iForest extensions are introduced, but they essentially still employ shallow, linear data partition, restricting their power in isolating true anomalies. Therefore, this paper proposes deep isolation forest. We introduce a new representation scheme that utilises casually initialised neural networks to map original data into random representation ensembles, where random axis-parallel cuts are subsequently applied to perform the data partition. This representation scheme facilitates high freedom of the partition in the original data space (equivalent to non-linear partition on subspaces of varying sizes), encouraging a unique synergy between random representations and random partition-based isolation. Extensive experiments show that our model achieves significant improvement over state-of-the-art isolation-based methods and deep detectors on tabular, graph and time series datasets;our model also inherits desired scalability from iForest. © 2022, CC BY.

关键词： Anomaly detection

Modeling Full Information with Graph Network for Joint Entity-Relation Extraction 21

学校读者我要写书评

暂无评论

Modeling Full Information with Graph Network for Joint Entit...

Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Qian Wan Luona Wei Xinhai Chen Jie Liu Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology China College of Systems Engineering National University of Defense Technology China Laboratory of Software Engineering for Complex Systems National University of Defense Technology China

ISBN: (纸本)9781450385053

Fully capturing contextual information and analyzing the association between entity semantics and type is helpful for joint extraction task: 1) The context can reflect the part of speech and semantics of entity. 2) The entity type is closely related to the relation between entities. Previous research used to simply embed the contextual information into shallow layer of the model, ignoring the association between entity semantics and type. In this paper, we propose a graph network with full-information modeling to explicitly model different-level information in the text. The contextual information of entity is dynamically embedded in each span representation to improve the reasoning ability. To capture the fine-grained association between the semantics and type of entity, the graph network uses the feature of entity types to generate edge information between different nodes. Experimental results show that our model outperforms previous models on the CoNLL04 dataset and obtains competitive results on the SciERC dataset in both entity recognition and relation extraction. Extensive additional experiments further verify the effectiveness of the model.

关键词： Natural Language processing Named Entity Recognition Graph Network Deep Learning Relation Extraction

DRAM failure prediction in AIOps: Empirical evaluation, challenges and opportunities

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Zhiyue Xu, Hongzuo Pang, Guansong Yu, Fengyuan Wang, Yijie Jian, Songlei Wang, Yongjun Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology China University of Adelaide Australia

DRAM failure prediction is a vital task in AIOps, which is crucial to maintain the reliability and sustainable service of large-scale data centers. However, limited work has been done on DRAM failure prediction mainly due to the lack of public available datasets. This paper presents a comprehensive empirical evaluation of diverse machine learning techniques for DRAM failure prediction using a large-scale multi-source dataset, including more than three millions of records of kernel, address, and mcelog data, provided by Alibaba Cloud through PAKDD 2021 competition. Particularly, we first formulate the problem as a multi-class classification task and exhaustively evaluate seven popular/state-of-the-art classifiers on both the individual and multiple data sources. We then formulate the problem as an unsupervised anomaly detection task and evaluate three state-of-the-art anomaly detectors. Further, based on the empirical results and our experience of attending this competition, we discuss major challenges and present future research opportunities in this task. © 2021, CC BY.

关键词： Web services

EmbRace: Accelerating Sparse Communication for distributed Training of NLP Neural Networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Shengwei Lai, Zhiquan Li, Dongsheng Zhang, Yiming Ye, Xiangyu Duan, Yabo National Key Laboratory of Parallel Distributed Processing Computer College National University of Defense Technology China Xiamen University China

distributed data-parallel training has been widely adopted for deep neural network (DNN) models. Although current deep learning (DL) frameworks scale well for dense models like image classification models, we find that these DL frameworks have relatively low scalability for sparse models like natural language processing (NLP) models that have highly sparse embedding tables. Most existing works overlook the sparsity of model parameters thus suffering from significant but unnecessary communication overhead. In this paper, we propose EmbRace, an efficient communication framework to accelerate communications of distributed training for sparse models. EmbRace introduces Sparsity-aware Hybrid Communication, which integrates AlltoAll and model parallelism into data-parallel training, so as to reduce the communication overhead of highly sparse parameters. To effectively overlap sparse communication with both backward and forward computation, EmbRace further designs a 2D Communication Scheduling approach which optimizes the model computation procedure, relaxes the dependency of embeddings, and schedules the sparse communications of each embedding row with a priority queue. We have implemented a prototype of EmbRace based on PyTorch and Horovod, and conducted comprehensive evaluations with four representative NLP models. Experimental results show that EmbRace achieves up to 2.41X speedup compared to the state-of-the-art distributed training baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

A regularized magnetotelluric inversion with a minimum support gradient constraint

学校读者我要写书评

暂无评论

Earthquake Science 2020年第3期33卷 130-140页

作者： Junjun Zhou Xiangyun Hu Tiaojie Xiao Institute of Geophysics and Geomatics China University of GeosciencesWuhan 430000China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 410073China

Magnetotelluric(MT)inversion is an illposed problem and the standard way to address it is through regularization,by adding a stabilizing functional to the data objective functional in order to obtain a stable *** traditional stabilizing functionals,in which a low-order differential operator is used,yield a smooth solution that may not be appropriate when anomalies occur in block *** some cases the focused imaging of a sharp electrical boundary is *** though various experiments have used stabilizing functionals that are suitable to obtain a clear and sharp boundary,such as the minimum support(MS)and the minimum gradient support(MGS)functionals,there are still some limitations in *** this paper,the minimum support gradient(MSG)is proposed as the stabilizing *** the uniform regularization framework,a regularized inversion with a variety of stabilizing functionals is performed and the inversion results are *** study shows that MSG inversion can not only obtain a clearly focused inversion but also a quite stable and robust one.

关键词： magnetotelluric focus inversion sharp boundary regulafization

OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhuang, Jia-Xin Huang, Xiansong Yang, Yang Chen, Jiancong Yu, Yue Gao, Wei Li, Ge Chen, Jie Zhang, Tong Peng Cheng Laboratory Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Electronic and Computer Engineering Peking University China National Laboratory for Parallel and Distributed Processing National University of Defense Technology China

In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platforms. Various medical image analysis methods, including 2D/3D medical image classification, segmentation, localisation, and detection, have been included in the toolbox with PyTorch and/or MindSpore implementations under heterogeneous NVIDIA and Huawei Ascend computing systems. To our best knowledge, OpenMedIA is the first open-source algorithm library providing compared PyTorch and MindSpore implementations and results on several benchmark datasets. The source codes and models are available at https://***/ OpenMedIA. © 2022, CC BY-NC-SA.

关键词： Open systems

FAAD:an unsupervised fast and accurate anomaly detection method for a multi-dimensional sequence over data stream

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2019年第3期20卷 388-404页

作者： Bin LI Yi-jie WANG Dong-sheng YANG Yong-mou LI Xing-kong MA Science and Technology on Parallel and Distributed Processing Laboratory College of ComputerNational University of Defense Technology Block Chain Research Institute of LianLian Pay

Recently, sequence anomaly detection has been widely used in many fields. Sequence data in these fields are usually multi-dimensional over the data stream. It is a challenge to design an anomaly detection method for a multi-dimensional sequence over the data stream to satisfy the requirements of accuracy and high speed. It is because:(1) Redundant dimensions in sequence data and large state space lead to a poor ability for sequence modeling;(2) Anomaly detection cannot adapt to the high-speed nature of the data stream, especially when concept drift occurs, and it will reduce the detection rate. On one hand, most existing methods of sequence anomaly detection focus on the single-dimension sequence. On the other hand, some studies concerning multi-dimensional sequence concentrate mainly on the static database rather than the data stream. To improve the performance of anomaly detection for a multi-dimensional sequence over the data stream, we propose a novel unsupervised fast and accurate anomaly detection(FAAD) method which includes three algorithms. First, a method called "information calculation and minimum spanning tree cluster" is adopted to reduce redundant dimensions. Second, to speed up model construction and ensure the detection rate for the sequence over the data stream, we propose a method called"random sampling and subsequence partitioning based on the index probabilistic suffix tree." Last, the method called "anomaly buffer based on model dynamic adjustment" dramatically reduces the effects of concept drift in the data stream. FAAD is implemented on the streaming platform Storm to detect multi-dimensional log audit *** with the existing anomaly detection methods, FAAD has a good performance in detection rate and speed without being affected by concept drift.

关键词： Data stream Multi-dimensional sequence Anomaly detection Concept drift Feature selection

Deep learning for social network information cascade analysis: A survey 5

学校读者我要写书评

暂无评论

Deep learning for social network information cascade analysi...

5th IEEE International Conference on Data Science in Cyberspace, DSC 2020

作者： Gao, Liqun Zhou, Bin Jia, Yan Tu, Hongkui Wang, Ye Chen, Chenguang Wang, Haiyang Zhuang, Hongwu National University of Defense Technology College of Computer ChangSha China National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory ChangSha China

ISBN: (纸本)9781728195582

The phenomenon of information dissemination in social networks is widespread, and Social Network Information Cascade Analysis (SNICA) aims to acquire valuable knowledge in the process of information dissemination in social networks. As the number, volume, and resolution of social network data increase rapidly, traditional social network data analysis methods, especially the analysis method of social network graph (SNG) data becoming overwhelmed in SNICA. Recently, deep learning models have changed this situation, and it has achieved success in SNICA with its powerful implicit feature extraction capabilities. In this paper, we provide a comprehensive survey of recent progress in applying deep learning techniques for SNICA. We first introduce related concepts and summarize the advantages of deep learning technology in SNICA. Then, we propose a general framework for deep learning technology, which applies to SNICA. Then, different SNICA application scenarios in the framework are classified and discussed according to user behavior analysis, information cascade analysis, rumor detection, and social network event analysis. Finally, we discuss the limitations of current work and suggest future directions. © 2020 IEEE.

关键词： Data mining

Big Data-aided Study of the Physical Process of Volume Ignition 6

学校读者我要写书评

暂无评论

Big Data-aided Study of the Physical Process of Volume Ignit...

2022 6th International Conference on Mechanics, Mathematics and Applied Physics, ICMMAP 2022

作者： Liu, Pan Zhou, Yinzhao Xiong, Wenbin Liu, Chencheng Liu, Jie Liu, Gongjie Tang, Zhangchun Gao, Qiang Tianfu Innovation Energy Establishment Chengdu610000 China Nuclear and Radiation Safety Center MEE Beijing100000 China Central South University of Forestry and Technology Changsha410000 China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China Beijng PARATERA Technology Corp. Ltd Beijing100000 China University of Electronic Science and Technology of China Chengdu610000 China

Volume ignition is a method of igniting a fuel as a whole by simultaneously achieving ignition conditions throughout the fuel zone. The basic criterion for ignition is that the thermonuclear energy is greater than the energy leakage at the fuel boundary, resulting in self-sustaining heating and deep combustion. Deuterium-tritium fuels are wrapped in medium to high Z media to reduce radiative leakage and achieve lower-temperature holistic ignition and non-equilibrium combustion, ultimately allowing the fuel to achieve high combustion efficiency. Volume ignition is the use of energy balance relations under the local thermodynamic equilibrium approximation to establish the energy balance equation for thermonuclear systems, and the system ignition threshold is obtained by solving this equation. By understanding the physical process, we believe that the non-equilibrium process is universal to the volume ignition process. Changes in external factors (density, boundaries, albedo, etc.) at the moment of ignition can have a significant impact on the development direction of the system, and an ignition system with a large surface density can nevertheless withstand a large amount of reverse work and continue to burn. The design of the ignition target tries to avoid these factors through margin design, but conversely, the rational use of these laws can further improve the design margin of the capsule. With the aid of big data, the volume ignition method is easier to calculate and has a shorter iteration time. The traditional way is to propose a model, set the material, and then perform the calculation while using big data can set any model and material for calculation. In this paper, a simple comparison will be made to find out that the efficiency of the physical design of a volume ignition target will be effectively improved with the aid of big data. Volume ignition targets can be used not only in Z-pinch-driven systems but also for laser-driven volume ignition. © Published un

关键词： Ignition