检索结果-内蒙古大学图书馆

arXiv 2025年

作者： He, Zhouyu Qiao, Peng Li, Rongchun Dou, Yong Tan, Yusong College of Computer Science and Technology National University of Defense Technology China National Key Laboratory of Parallel and Distributed Computing National University of Defense Technology China

As the demands for superior agents grow, the training complexity of Deep Reinforcement Learning (DRL) becomes higher. Thus, accelerating training of DRL has become a major research focus. Dividing the DRL training process into subtasks and using parallel computation can effectively reduce training costs. However, current DRL training systems lack sufficient parallelization due to data assignment between subtask components. This assignment issue has been ignored, but addressing it can further boost training efficiency. Therefore, we propose a high-throughput distributed RL training system called TianJi. It relaxes assignment dependencies between subtask components and enables event-driven asynchronous communication. Meanwhile, TianJi maintains clear boundaries between subtask components. To address convergence uncertainty from relaxed assignment dependencies, TianJi proposes a distributed strategy based on the balance of sample production and consumption. The strategy controls the staleness of samples to correct their quality, ensuring convergence. We conducted extensive experiments. TianJi achieves a convergence time acceleration ratio of up to 4.37 compared to related comparison systems. When scaled to eight computational nodes, TianJi shows a convergence time speedup of 1.6 and a throughput speedup of 7.13 relative to XingTian, demonstrating its capability to accelerate training and scalability. In data transmission efficiency experiments, TianJi significantly outperforms other systems, approaching hardware limits. TianJi also shows effectiveness in on-policy algorithms, achieving convergence time acceleration ratios of 4.36 and 2.95 compared to RLlib and XingTian. TianJi is accessible at https://***/HiPRL/***. © 2025, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hemo-FS-SAM2: Few-Shot Tuning on Hemorrhage Segmentation of Segment Anything Model 2

Hemo-FS-SAM2: Few-Shot Tuning on Hemorrhage Segmentation of ...

引用

Advanced Algorithms and Control Engineering (ICAACE), International Conference on

作者： Xi Wang Peng Qiao Yong Dou National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology National University of Defense Technology Changsha China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

Surgical hemorrhage is a common occurrence in surgeries. Accurate segmentation of hemorrhage regions is important for surgical navigation and post-operative assessment. Some segmentation models focused on medical images, but its performance on hemorrhage data is limited. Besides, there is an essential challenge to annotate a large number of hemorrhage data, and previous segmentation methods struggle with complex hemorrhage characteristics like unclear boundaries and scattered targets. The Segment Anything Model 2 (SAM2) shows an significant zero-shot ability in general image segmentation, and is generalizable to fine-tuned on downstream tasks. However, it often faces limitations in hemorrhage segmentation task that lacking annotations. This paper proposes a fine-tuning approach for SAM2, significantly improving its performance on hemorrhage segmentation tasks with limited data. Our method provides better segmentation performance on few-shot hemorrhage data than SAM and SAM2 based models.

关键词： Image segmentation Adaptation models Accuracy Annotations Shape Surgery Data models Hemorrhaging Tuning Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Smoothing Point Adjustment-Based Evaluation of Time Series Anomaly Detection

Smoothing Point Adjustment-Based Evaluation of Time Series A...

引用

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

作者： Mingyu Liu Yijie Wang Hongzuo Xu Xiaohui Zhou Bin Li Yongjun Wang Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha China

Anomalies in time series appear consecutively, forming anomaly segments. Applying the classical point-based evaluation metrics to evaluate the detection performance of segments leads to considerable underestimation, so most related studies resort to point adjustment. This operation treats all points as true positives within a segment equally when only one individual point alarms, resulting in significant overestimation and creating an illusion of superior performance. This paper proposes smoothing point adjustment, a novel range-based evaluation protocol for time series anomaly detection. Our protocol reflects detection performance impartially by carefully considering the specific location and frequency of alarms in the raw results. It is achieved by smoothly determining the adjustment range and rewarding early detection via a ranging function and a rewarding function. Compared with other evaluation metrics, experiments on different datasets show that our protocol can yield a performance ranking of various methods more consistent with the desired situation.

关键词： Protocols Smoothing methods Time series analysis Detectors Signal processing Distance measurement Acoustics

来源：评论

学校读者我要写书评

暂无评论

Effective Anomaly Detection Based on Reinforcement Learning in Network Traffic Data 27

Effective Anomaly Detection Based on Reinforcement Learning ...

引用

27th IEEE International Conference on parallel and distributed Systems, ICPADS 2021

作者： Wang, Zhongyang Wang, Yijie Xu, Hongzuo Wang, Yongjun National University of Defense Technology Science and Technology on Parallel Distributed Processing Laboratory College of Computer China

ISBN: (纸本)9781665408783

Mixed-type data with both categorical and numerical features are ubiquitous in network security, but the existing methods are minimal to deal with them. Existing methods usually process mixed-type data through feature conversion, whereas their performance is downgraded by information loss and noise caused by the transformation. Meanwhile, existing methods usually superimpose domain knowledge and machine learning in which fixed thresholds are used. It cannot dynamically adjust the anomaly threshold to the actual scenario, resulting in inaccurate anomalies obtained, which results in poor performance. To address these issues, this paper proposes a novel Anomaly Detection method based on Reinforcement Learning, termed ADRL, which uses reinforcement learning to dynamically search for thresholds and accurately obtain anomaly candidate sets, fusing domain knowledge and machine learning fully and promoting each other. Specifically, ADRL uses prior domain knowledge to label known anomalies and uses entropy and deep autoencoder in the categorical and numerical feature spaces, respectively, to obtain anomaly scores combining with known anomaly information, which are integrated to get the overall anomaly scores via a dynamic integration strategy. To obtain accurate anomaly candidate sets, ADRL uses reinforcement learning to search for the best threshold. Detailedly, it initializes the anomaly threshold to get the initial anomaly candidate set and carries on the frequent rule mining to the anomaly candidate set to form the new knowledge. Then, ADRL uses the obtained knowledge to adjust the anomaly score and get the score modification rate. According to the modification rate, different threshold modification strategies are executed, and the best threshold, that is, the threshold under the maximum modification rate, is finally obtained, and the modified anomaly scores are obtained. The scores are used to re-carry out machine learning to improve the algorithm's accuracy for anomalo

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

The parallelized Cuckoo Filter for Cold Data Representation 23

The Parallelized Cuckoo Filter for Cold Data Representation

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Sun, Bowen Luo, Lailong Li, Shangsen Chen, Yingwen Guo, Deke College of Computer National University of Defense Technology China National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory China College of Computer National University of Defense Technology National Lab for Parallel and Distributed Processing China

ISBN: (纸本)9781665494571

Cold data contributes a large portion of the big data today and is usually stored in secondary storage. Various sketch data structures are implemented to represent the stored elements and provide constant-time membership queries. Considering the large volume and infrequent access of cold data, we envision three rationales of cold data representation: 1) parallelized insertion, 2) accurate representation, and 3) constant-time query/deletion. The existing sketches, however, fail to achieve these rationales simultaneously. To this end, we propose a novel sketch named parallelized cuckoo Filter (PCF) in this paper. PCF divides the standard cuckoo filter into multiple homogenous segments. An additional hash function is introduced to assign an element to a segment. The element will be inserted into the selected segment. With such a design, element insertions in PCF can be naturally parallelized. Besides, as a variant of the cuckoo filter, PCF naturally realizes the accurate representation and constant-time query/deletion requirements. Comprehensive experiments further indicate that PCF achieves the three rationales simultaneously. © 2021 IEEE.

关键词： Hash functions Smart cities Big Data Data structures Standards

来源：评论

学校读者我要写书评

暂无评论

Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion

arXiv

引用

arXiv 2024年

作者： Shan, Yongxue Zhou, Jie Peng, Jie Zhou, Xin Yin, Jiaqian Wang, Xiaodong National Key Laboratory of Parallel and Distributed Computing College of Computer National University of Denfense Technology Changsha China

In the task of Knowledge Graph Completion (KGC), the existing datasets and their inherent subtasks carry a wealth of shared knowledge that can be utilized to enhance the representation of knowledge triplets and overall performance. However, no current studies specifically address the shared knowledge within KGC. To bridge this gap, we introduce a multi-level Shared Knowledge Guided learning method (SKG) that operates at both the dataset and task levels. On the dataset level, SKG-KGC broadens the original dataset by identifying shared features within entity sets via text summarization. On the task level, for the three typical KGC subtasks – head entity prediction, relation prediction, and tail entity prediction – we present an innovative multi-task learning architecture with dynamically adjusted loss weights. This approach allows the model to focus on more challenging and underperforming tasks, effectively mitigating the imbalance of knowledge sharing among subtasks. Experimental results demonstrate that SKG-KGC outperforms existing text-based methods significantly on three well-known datasets, with the most notable improvement on WN18RR (MRR: 66.6%→72.2%, Hit@1: 58.7%→67.0%). Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Feature and Performance Comparison of FaaS Platforms 14

Feature and Performance Comparison of FaaS Platforms

引用

14th IEEE International Conference on Software Engineering and Service science, ICSESS 2023

作者： Ma, Penghui Shi, Peichang Yi, Guodong College of Computer Science National University of Defense Technology National Key Laboratory of Parallel and Distributed Processing Changsha410073 China College of Computer Science National University of Defense Technology Key Laboratory of Software Engineering for Complex Systems Changsha410073 China Xiangjiang Lab Changsha410073 China School of Advanced Interdisciplinary Studies Hunan University of Technology and Business Changsha410073 China

ISBN: (纸本)9798350336269

With serverless computing offering more efficient and cost-effective application deployment, the diversity of serverless platforms presents challenges to users, including platform lock-in and costly migration. Moreover, due to the black box nature of function computing, traditional performance benchmarking methods are not applicable, necessitating new studies. This article presents a detailed comparison of six major public cloud function computing platforms and introduces a benchmarking framework for function computing performance. This framework aims to help users make comprehensive comparisons and select the most suitable platform for their specific needs. © 2023 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Funnel: An Efficient Sparse Attention Accelerator with Multi-Dataflow Fusion

Funnel: An Efficient Sparse Attention Accelerator with Multi...

引用

International Symposium on parallel and distributed Processing with Applications, ISPA

作者： Shenghong Ma Jinwei Xu Jingfei Jiang Yaohua Wang Dongsheng Li National Key Laboratory of Parallel and Distributed Computing College of Computer National University of Defense Technology Changsha China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

The self-attention mechanism is the core component of Transformer, which provides a powerful ability to understand the sequence context. However, the self-attention mechanism also suffers from a large amount of redundant computation. Model sparsification can effectively reduce computational load, but the irregularity of non-zeros introduced by sparsification significantly decreases hardware efficiency. This paper proposes Funnel, an accelerator that dynamically predicts sparse attention patterns and efficiently processes unstructured sparse data. Firstly, we adopt a fast quantization method based on lookup table to minimize the cost of sparse patterns prediction. Secondly, we propose Funnel Computing Unit (FCU), a hardware architecture that efficiently handles sparse attention through multi-dataflow fusion. Sampled Dense-Dense Matrix Multiplication (SDDMM) and Sparse-Dense Matrix Multiplication (SpMM) are core components of sparse attention mechanism. FCU unifies the computation ways of matrix inner product and row-wise product to support SDDMM and SpMM at the same time, which greatly reduces the storage and movement overhead of intermediate results. Lastly, we devise a lightweight buffer and data tiling strategy tailored to the proposed accelerator, aimed at enhancing data reuse. Experiments demonstrate that our accelerator achieves 0.10-0.25 sparsity with small accuracy loss. When computing the self-attention layer, it attains hardware efficiency ranging from 60% to 85%. Compared to CPU and GPU, it achieves 5.60x and 8.20x speedup. Compared to the state-of-the-art attention accelerators A 3 , SpAtten, FTRANS, and Sanger, it achieves 7.37x, 4.52x, 9.58x, and 3.08x speedup.

关键词： Quantization (signal) Graphics processing units computer architecture Transformer cores Transformers Prediction algorithms Hardware Spatiotemporal phenomena Sparse matrices Sorting

来源：评论

学校读者我要写书评

暂无评论

Handwritten Digital Image Recognition based on Fusion of Multiple Machine Vision Algorithms 6

Handwritten Digital Image Recognition based on Fusion of Mul...

引用

6th International Conference on Information Technologies and Electrical Engineering, ICITEE 2023

作者： Lin, Bingrong Yang, Zhi Yang, Minsheng Xie, Xiaole Wang, Xiong Liu, Huiting Lan, Yang College of Computer and Electrical Engineering Huan University of Arts and Science China College of Computer and Electrical Engineering Huan University of Arts and Science Key Laboratory of Distributed Electric Propulsion Vehicle Control Technology China

ISBN: (纸本)9798400708299

Handwritten digit recognition technology is increasingly used in a wide range of fields, but the recognition rate still has room for further improvement. Currently, there are a large number of studies focusing on the use of activation functions to improve the handwritten digit recognition rate, compared with ReLU, Sigmod and other activation functions, this paper chooses to take the Mish activation function to optimise the handwritten digit recognition algorithm, using Pytorch machine learning framework, designed a deep convolutional neural network model based on the MNIST dataset to carry out digit recognition, and to improve the accuracy of model recognition through the learning of image features for digit classification to improve the model recognition accuracy. The experimental results show that the Mish activation function can increase the accuracy of handwritten digit recognition to 99%. Keywords: Handwritten digit recognition, Deep convolutional neural network, Mish activation function, MNIST Dataset, Pytorch © 2023 ACM.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Cooperative Air-Ground Instant Delivery by UAVs and Crowdsourced Taxis 40

Cooperative Air-Ground Instant Delivery by UAVs and Crowdsou...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Gao, Junhui Wang, Qianru Zhang, Xin Shi, Juan Zhao, Xiang Han, Qingye Pan, Yan School of Computer Science Northwestern Polytechnical University China School of Computer Science and Technology Xidian University China Air Force Engineering University China National University of Defense Technology Laboratory for Big Data and Decision China School of Management Science and Real Estate Chongqing University China National University of Defense Technology National Key Laboratory of Information Systems Engineering China National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing China

ISBN: (纸本)9798350317152

Instant delivery has become a fundamental service in people's daily lives. Different from the traditional express service, the instant delivery has a strict shipping time constraint after being ordered. However, the labor shortage makes it challenging to realize efficient instant delivery. To tackle the problem, researchers have studied to introduce vehicles (i.e., taxis) or Unmanned Aerial Vehicles (UAVs or drones) into instant delivery tasks. Unfortunately, the delivery detour of taxis and the limited battery of UAVs make it hard to meet the rapidly increasing instant delivery demands. Under this circumstance, this paper proposes an air-ground cooperative instant delivery paradigm to maximize the delivery performance and meanwhile minimize the negative effects on the taxi passengers. Specifically, a data-driven delivery potential-demands-aware cooperative strategy is designed to improve the overall delivery performance of both UAVs and taxis as well as the taxi passengers' experience. The experimental results show that the proposed method improves the delivery number by 30.1% and 114.5% compared to the taxi-based and UAV-based instant delivery respectively, and shortens the delivery time by 35.7% compared to the taxi-based instant delivery. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

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：