检索结果-内蒙古大学图书馆

Deep anomaly detection with partition contrastive learning for tabular data

Data Mining and Knowledge Discovery 2025年第4期39卷 1-38页

作者： Li, Yizhou Wang, Yijie Xu, Hongzuo Li, Bin Zhou, Xiaohui National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology Changsha China Intelligent Game and Decision Lab (IGDL) Beijing China

Self-supervised anomaly detection (AD) methods define transformations and surrogate tasks to deeply learn data “normality”, presenting superior performance. Different from most existing work designed for images, this paper considers self-supervised AD for tabular data, which has two desiderata: (i) transformation operations need to generate diverse transformed samples for downstream contrastive learning; (ii) the learning of surrogate tasks is required to perceive the semantics of tabular data, i.e., local–global patterns including intra-instance regularities and inter-instance structures. Related studies devise applicable transformations, but their surrogate tasks often neglect the inter-instance structures, failing to describe comprehensive data “normality" accurately. To fill these gaps, this paper proposes a novel partition contrastive learning-based anomaly detection method. We first devise a new transformation. Transformed samples are created by representing sub-vectors generated from different partitions of the whole feature space, during which different feature couplings are embedded in the transformed samples to make them sufficiently diverse. To capture intra-instance regularities, our approach learns a representation space where the transformed samples repel each other while concurrently resembling their corresponding spatial centers. A constraint is posed on the frames of these spatial centers to preserve their similarities between the corresponding original instances, facilitating the learning of inter-instance structures. The synergy of these two learning objectives encourages the modeling of tabular data semantics, thereby comprehensively modeling data “normality”. Abnormal degrees of the testing data are obtained by evaluating whether they conform to these learned patterns shared in the majority of data. Extensive experiments show that our approach achieves significant improvements (13% AUC-ROC and 30% AUC-PR) over state-of-the-art AD methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Time Series Anomaly Detection with Local Temporal Pattern Learning

Deep Time Series Anomaly Detection with Local Temporal Patte...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yizhou Li Yijie Wang Hongzuo Xu Xiaohui Zhou National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology Changsha China Intelligent Game and Decision Lab (IGDL) Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Self-supervised time series anomaly detection (TSAD) demonstrates remarkable performance improvement by extracting high-level data semantics through proxy tasks. Nonetheless, most existing self-supervised TSAD techniques rely on manual- or neural-based transformations when designing proxy tasks, overlooking the intrinsic temporal patterns of time series. This paper proposes a local temporal pattern learning-based time series anomaly detection (LTPAD). LTPAD first generates sub-sequences. Pairwise sub-sequences naturally manifest proximity relationships along the time axis, and such correlations can be used to construct supervision and train neural networks to facilitate the learning of temporal patterns. Time intervals between two sub-sequences serve as labels for sub-sequence pairs. By classifying these labeled data pairs, our model captures the local temporal patterns of time series, thereby modeling the temporal pattern-aware "normality". Abnormal scores of testing data are acquired by evaluating their conformity to these learned patterns shared in training data. Extensive experiments show that LTPAD significantly outperforms state-of-the-art competitors.

关键词： Time series analysis Semantics Neural networks Training data Manuals Signal processing Data models Speech processing Anomaly detection Testing

来源：评论

学校读者我要写书评

暂无评论

Minimizing transformer inference overhead using controlling element on Shenwei AI accelerator

引用

Frontiers of Information Technology & Electronic Engineering 2025年第4期26卷 605-622页

作者： Zhao, Yulong Wu, Chunzhi Wang, Yizhuo Zhang, Lufei Zhang, Yaguang Shen, Wenyuan Fan, Hao Fang, Hankang Qin, Yi Liu, Xin State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China School of Non-Commissioned Officer Space Engineering University Beijing China National Supercomputing Center in Wuxi Wuxi China Zhejiang Lab Hangzhou China National Research Centre of Parallel Computer Engineering and Technology Beijing China

Transformer models have become a cornerstone of various natural language processing (NLP) tasks. However, the substantial computational overhead during the inference remains a significant challenge, limiting their deployment in practical applications. In this study, we address this challenge by minimizing the inference overhead in transformer models using the controlling element on artificial intelligence (AI) accelerators. Our work is anchored by four key contributions. First, we conduct a comprehensive analysis of the overhead composition within the transformer inference process, identifying the primary bottlenecks. Second, we leverage the management processing element (MPE) of the Shenwei AI (SWAI) accelerator, implementing a three-tier scheduling framework that significantly reduces the number of host-device launches to approximately 1/10 000 of the original PyTorch-GPU setup. Third, we introduce a zero-copy memory management technique using segment-page fusion, which significantly reduces memory access latency and improves overall inference efficiency. Finally, we develop a fast model loading method that eliminates redundant computations during model verification and initialization, reducing the total loading time for large models from 22 128.31 ms to 1041.72 ms. Our contributions significantly enhance the optimization of transformer models, enabling more efficient and expedited inference processes on AI accelerators.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EDGE-ORIENTED HEXAGONAL ELEMENTS

引用

Journal of Computational Mathematics 2007年第4期25卷 430-439页

作者： Chao Yang Jiachang Sun Parallel Computing Lab. Institute of Software Chinese Academy of Sciences Beijing 100080 China

In this paper, two new nonconforming hexagonal elements are presented, which are based on the trilinear function space Q1^（3） and are edge-oriented, analogical to the case of the rotated Q1 quadrilateral element. A priori error estimates are given to show that the new elements achieve first-order accuracy in the energy norm and second-order accuracy in the L^2 norm. This theoretical result is confirmed by the numerical tests.

关键词： Nonconforming finite element method Hexagonal element Q1 element.

来源：评论

学校读者我要写书评

暂无评论

PALM: parallel architecture friendly latchfree modifications to B+ trees on manycore processors 37

PALM: Parallel architecture friendly latchfree modifications...

引用

37th International Conference on Very Large Data Bases, VLDB 2011

作者： Sewall, Jason Chhugani, Jatin Kim, Changkyu Satish, Nadathur Dubey, Pradeep Parallel Computing Lab Intel Corporation United States

Concurrency control on B+ trees is primarily achieved with latches, but serialization and contention can hinder scalability. As core counts on current processors increase, it is imperative to develop scalable latch-free techniques for concurrency control. We present PALM, a novel technique for performing multiple concurrent queries on in-memory B+ trees. PALM is based on the Bulk Synchronous parallel model, which guarantees freedom from deadlocks and race conditions. Input queries are grouped and processed in atomic batches, and work proceeds in stages that preclude contention. Transitions between stages are accomplished with scalable point-to-point communication. PALM exploits dataand thread-level parallelism on modern many-core architectures, and performs 40M1 updates/second on trees with 128M keys, and 128M updates/second on trees with 512K keys on the latest CPU architectures. Our throughput is 2.3X-19X that of state-of-theart concurrent update algorithms on in-memory B+ trees. PALM obtains close to peak throughput at very low response times of less than 350μs, even for large trees. We also evaluate PALM on the Intel® Many Integrated Core (Intel® MIC) architecture, and demonstrate a speedup of 1.5-2.1X for out-of-cache tree sizes on an Intel® Knights Ferry over a pair of Intel® Xeon® processors DP X5680 (Westmere-EP) in a dual-socket configuration. © 2011 VLDB Endowment.

关键词： Concurrency control

来源：评论

学校读者我要写书评

暂无评论

A CONSTANT-TIME parallel SORTING ALGORITHM AND ITS OPTICAL IMPLEMENTATION

引用

IEEE MICRO 1995年第3期15卷 60-71页

作者： LOURI, A HATCH, JA NA, JH Opt. Comput. & Parallel Process. Lab. Arizona Univ. Tucson AZ USA Trimble Navigation Texas Optical Computing and Parallel Processing Laboratory University of Arizona

High-speed electronic sorting networks are difficult to implement with VLSI technology because of the dense and global connectivity required. Optics eliminates this bottleneck by offering global interconnections, massive parallelism, and noninterfering communications. We present a parallel sorting algorithm and its efficient optical implementation using currently available optical hardware. The algorithm sorts n data elements in a few steps, independent of the number of elements to be sorted. Thus, it is a constant-time sorting algorithm, that is, O(1) time.

关键词： Sorting parallel Sorting Optical computing parallel Processing

来源：评论

学校读者我要写书评

暂无评论

Distributed Hessian-free optimization for deep neural network 31

Distributed Hessian-free optimization for deep neural networ...

引用

31st AAAI Conference on Artificial Intelligence, AAAI 2017

作者： He, Xi Mudigere, Dheevatsa Smelyanskiy, Mikhail Takáč, Martin Industrial and Systems Engineering Lehigh University United States Parallel Computing Lab Intel Labs India Parallel Computing Lab Intel Labs SC United States

ISBN: (纸本)9781577357865

Training deep neural network is a high dimensional and a highly non-convex optimization problem. In this paper, we revisit Hessian-free optimization method for deep networks with negative curvature direction detection. We also develop its distributed variant and demonstrate superior scaling potential to SGD, which allows more efficiently utilizing larger computing resources thus enabling large models and faster time to obtain desired solution. We show that these techniques accelerate the training process for both the standard MNIST dataset and also the TIMIT speech recognition problem, demonstrating robust performance with upto an order of magnitude larger batch sizes. This increased scaling potential is illustrated with near linear speed-up on upto 32 CPU nodes for a simple 4-layer network. © Copyright 2017, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

MIXED PRECISION TRAINING OF CONVOLUTIONAL NEURAL NETWORKS USING INTEGER OPERATIONS 6

MIXED PRECISION TRAINING OF CONVOLUTIONAL NEURAL NETWORKS US...

引用

6th International Conference on Learning Representations, ICLR 2018

作者： Das, Dipankar Mellempudi, Naveen Mudigere, Dheevatsa Kalamkar, Dhiraj Avancha, Sasikanth Banerjee, Kunal Sridharan, Srinivas Vaidyanathan, Karthik Kaul, Bharat Georganas, Evangelos Heinecke, Alexander Dubey, Pradeep Corbal, Jesus Shustrov, Nikita Dubtsov, Roma Fomenko, Evarist Pirogov, Vadim Parallel Computing Lab Intel Labs India Parallel Computing Lab Intel Labs SC Product Architecture Group Intel OR United States Software Services Group Intel OR United States

The state-of-the-art (SOTA) for mixed precision training is dominated by variants of low precision floating point operations, and in particular FP16 accumulating into FP32 Micikevicius et al. (2017). On the other hand, while a lot of research has also happened in the domain of low and mixed-precision Integer training, these works either present results for non-SOTA networks (for instance only AlexNet for ImageNet-1K), or relatively small datasets (like CIFAR-10). In this work, we train state-of-the-art visual understanding neural networks on ImageNet-1K dataset, with Integer operations on General Purpose (GP) hardware. In particular, we focus on Integer Fused-Multiply-and-Accumulate (FMA) operations which take two pairs of INT16 operands and accumulate results into an INT32 *** propose a shared exponent representation of tensors, and develop a Dynamic Fixed Point (DFP) scheme suitable for common neural network operations. The nuances of developing an efficient integer convolution kernel is examined, including methods to handle overflow of the INT32 accumulator. We implement CNN training for ResNet-50, GoogLeNet-v1, VGG-16 and AlexNet;and these networks achieve or exceed SOTA accuracy within the same number of iterations as their FP32 counterparts without any change in hyper-parameters and with a 1.8X improvement in end-to-end training throughput. To the best of our knowledge these results represent the first INT16 training results on GP hardware for ImageNet-1K dataset using SOTA CNNs and achieve highest reported accuracy using half precision representation. © 2017 International Conference on Learning Representations, ICLR. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards a matrix-oriented strided interface in OpenSHMEM 14

Towards a matrix-oriented strided interface in OpenSHMEM

引用

8th International Conference on Partitioned Global Address Space Programming Models, PGAS 2014

作者： Hammond, Jeff R. Extreme Scalability Group Parallel Computing Lab Intel Corporation United States

New communication routines are proposed for OpenSHMEM to allow the efficient implementation of distributed matrix computations. Copyright is held by the owner/author(s). Publication rights licensed to ACM.

ISBN: (纸本)9781450332477

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

An online service-oriented performance profiling tool for cloud computing systems

引用

Frontiers of Computer Science 2013年第3期7卷 431-445页

作者： Haibo MI Huaimin WANG Yangfan ZHOU Michael Rung-Tsong LY~ Hua CAI Gang YIN National Lab for Parallel & Distributed Processing National University of Defense Technology Changsha 410073 China Shenzhen Research Institute The Chinese University of Hong Kong Shenzhen 518000 China Computing Platform Alibaba Cloud Computing Company Hangzhou 310000 China

The growing scale and complexity of component interactions in cloud computing systems post great challenges for operators to understand the characteristics of system performance. Profiling has long been proved to be an effective approach to performance analysis; however, existing approaches confront new challenges that emerge in cloud computing systems. First, the efficiency of the profiling becomes of critical concern; second, service-oriented profiling should be considered to support separation-of-concerns performance analysis. To address the above issues, in this paper, we present P-Tracer, an online performance profiling tool specifically tailored for cloud computing systems. P-Tracer constructs a specific search engine that proactively processes performance logs and generates a particular index for fast queries; second, for each service, P-Tracer retrieves a statistical insight of performance characteristics from multi-dimensions and provides operators with a suite of web-based interfaces to query the critical information. We evaluate P- Tracer in the aspects of tracing overheads, data preprocessing scalability and querying efficiency. Three real-world case studies that happened in Alibaba cloud computing platform demonstrate that P-Tracer can help operators understand soft-ware behaviors and localize the primary causes of performance anomalies effectively and efficiently.

关键词： cloud computing performance profiling performance anomaly visual analytics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：