检索结果-内蒙古大学图书馆

Short Tail:taming tail latency for erasure-code-based in-memory systems

Frontiers of Information Technology & Electronic engineering 2022年第11期23卷 1646-1657页

作者： Yun TENG Zhiyue LI Jing HUANG Guangyan ZHANG College of Computer Science and Technology Jilin UniversityChangchun 130012China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun 130012China Beijing National Research Center for Information Science and Technology(Tsinghua University) Beijing 100084China

In-memory systems with erasure coding(EC)enabled are widely used to achieve high performance and data ***,as the scale of clusters grows,the server-level fail-slow problem is becoming increasingly frequent,which can create long tail *** influence of long tail latency is further amplified in EC-based systems due to the synchronous nature of multiple EC *** this paper,we propose an EC-enabled in-memory storage system called ShortTail,which can achieve consistent performance and low latency for both reads and ***,ShortTail uses a lightweight request monitor to track the performance of each memory node and identify any fail-slow ***,ShortTail selectively performs degraded reads and redirected writes to avoid accessing fail-slow ***,ShortTail posts an adaptive write strategy to reduce write amplification of small *** implement ShortTail on top of Memcached and compare it with two baseline *** experimental results show that ShortTail can reduce the P99 tail latency by up to 63.77%;it also brings significant improvements in the median latency and average latency.

关键词： Erasure code In-memory system Node fail-slow Small write Tail latency

来源：评论

学校读者我要写书评

暂无评论

Convergence-Aware Optimal Checkpointing for Exploratory Deep Learning Training Jobs

SSRN

引用

SSRN 2024年

作者： Li, Hongliang Wang, Zichen Zhao, Hairui Zhang, Meng Li, Xiang Xu, Haixiao College of Computer Science and Technology Jilin University Qianjin street 2699 Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education Qianjin street 2699 Jilin Changchun130012 China High Performance Computing Center Qianjin street 2699 Jilin Changchun130012 China

Training Deep Learning (DL) models are becoming more time-consuming, thus interruptions to the training processes are inevitable. Existing fault-tolerant work adopted checkpoint/recovery mechanism from traditional HPC platforms that makes periodical persistent copies of model states to save execution progress. These checkpoints have fixed time intervals that they are evenly placed across the training. We can obtain an optimal checkpointing interval for an HPC job with the precondition that the progress of a job is proportional to its execution time. Unfortunately, it is not the case in DL model training where a DL training job yields diminishing returns across its lifetime. It makes the early progress of a DL training job more valuable than the later ones. Even placement of checkpoints would either increase the risks in the early stages or waste resources overprotecting the latter stages. Meanwhile, the issue can get amplified for exploratory training jobs, where early terminations are common. Moreover, in data parallelism, the state-of-art quality-driven scheduling strategies allocate more resources for the early stages of a job than the later ones to accelerate the training progress which further amplifies the issue. This paper introduces a novel checkpointing interval problem for exploratory DL training jobs based on model convergence progress. We present COCI, an approach to compute optimal checkpointing configuration for a DL training job, minimizing the fault-tolerant overhead, including checkpointing cost and recovery cost. We implement COCI based on state-of-art iteration-level checkpointing mechanism, as a pluggable module compatible with PyTorch. COCI requires no extra user input. We conduct comprehensive evaluations with real DL application setups. The experimental results show that COCI reduces up to 40.18% fault-tolerant overhead compared to existing state-of-the-art DL fault-tolerant methods in serial scenario, 57.26% in data parallel scenario and 63.8

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

arXiv

引用

arXiv 2025年

作者： Chen, Haipeng Wu, Sifan Wang, Zhigang Yin, Yifang Jiao, Yingying Lyu, Yingda Liu, Zhenguang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China A*STAR Singapore Public Computer Education and Research Center Jilin University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An Adversarial Complementary Erasing Network for Salient Object Detection in Optical Remote Sensing Images

SSRN

引用

SSRN 2023年

作者： Liang, Yanhua Qin, Guihe Sun, Minghui Qin, Jun Yan, Jie Zhang, Zhonghan College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China School of Computer Science and Technology Changchun University of Science and Technology Changchun130012 China

Salient object detection in optical remote sensing images (RSI-SOD) aims to locate and extract visually discriminative objects or regions, which has attracted more and more attention from the community. The key challenge of RSI-SOD lies in the characteristics of optical RSIs, such as scale diversification of salient objects, irregular edges, and cluttered backgrounds. In this paper, we strive to embrace challenges towards effective and efficient RSI-SOD. To this end, we develop a framework, termed Adversarial Complementary Erasing Network (ACENet), which comprehensively mines discriminative features of different layers from foreground, background, local and global perspectives to perform robust and accurate saliency detection. Specifically, ACENet is a typical encoder-decoder structure that embeds Adversarial Erasing Synthesis Module (AESM) in multi-scale encoding features to fully explore more useful and complete representations. In AESM, we introduce Adversarial Discriminant Information Mining (ADIM) component to facilitate adaptive adjustment between salient features and background, further enabling more representative and strong integrity feature generation. Experimental results on three datasets prove that our ACENet significantly outperforms cutting-edge SOD models both qualitatively and quantitatively with a quick reasoning speed of 76 FPS. Code will be available at https://***/Liangyh18/ACENet. © 2023, The Authors. All rights reserved.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Fuzzy Clustering Based Collaborative Filtering Algorithm for Time-Aware POI Recommendation 3

A Fuzzy Clustering Based Collaborative Filtering Algorithm f...

引用

2020 3rd International Conference on Modeling, Simulation and Optimization Technologies and Applications, MSOTA 2020

作者： Yin, Minghao Liu, Yanheng Zhou, Xu Sun, Geng College of Computer Science and Technology Jilin University Changchun Jilin China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun Jilin China Center for Computer Fundamental Education Jilin University Changchun Jilin China

Location based social network develops and gets widely concern along with the population and widespread use of mobile. Point of interest(POI) recommendation become one of the most widely application among location-based service. To get better POI recommendation performance, a fuzzy clustering based collaborative filtering algorithm (FCCF) for time-Aware POI recommendation is proposed in this paper. It first constructs the user feature vector from users' check-in behaviours. Individual's check-in behaviour can be under the influence of location region and time slots, so user's feature consists of two parts. One is the vising frequency of each user in different location regions, and the other is the vising frequency of each user in different time slots. Next fuzzy c-means is adopted due to its simplicity to group users according to user feature vector. Then the user similarity computation can be limited in the similar small user groups. In the end, a collaborative filtering algorithm is applied to recommend a number of top-N POIs at a given time for the target user. Some experiments are conducted and the comparative results on Foursquare and Gowalla show that FCCF has higher precision and recall value than the comparative algorithms. © Published under licence by IOP Publishing Ltd.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

PBCounter: Weighted Model Counting on Pseudo-Boolean Formulas

arXiv

引用

arXiv 2023年

作者： Lai, Yong Xu, Zhenghang Yin, Minghao College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China School of Computer Science and Information Technology Northeast Normal University Changchun130017 China

In Weighted Model Counting (WMC), we assign weights to literals and compute the sum of the weights of the models of a given propositional formula where the weight of an assignment is the product of the weights of its literals. The current WMC solvers work on Conjunctive Normal Form (CNF) formulas. However, CNF is not a natural representation for human-being in many applications. Motivated by the stronger expressive power of pseudo-Boolean (PB) formulas than CNF, we propose to perform WMC on PB formulas. Based on a recent dynamic programming algorithm framework called ADDMC for WMC, we implement a weighted PB counting tool PBCounter. We compare PBCounter with the state-of-the-art weighted model counters SharpSAT-TD, ExactMC, D4, and ADDMC, where the latter tools work on CNF with encoding methods that convert PB constraints into a CNF formula. The experiments on three domains of benchmarks show that PBCounter is superior to the model counters on CNF formulas. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Optimization Approach for Secure Communications Based on Collaborative Beamforming in UAV Networks

A Multi-objective Optimization Approach for Secure Communica...

引用

IEEE Conference on Wireless Communications and Networking

作者： Xinrong Guo Fang Mei Geng Sun Tingting Zheng College of Software Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China College of Electrical and Computer Engineering University of Waterloo Waterloo Canada

With the rapid development of wireless communication, unmanned aerial vehicle (UAV) networks have received extensive attention and been applied in many fields, but some challenges exist in their applications, such as the issue of security when implementing communication. In this paper, a virtual antenna array (VAA) is formed in multiple UAV units using collaborative beamforming (CB) technology. Under the interference of multiple eavesdroppers, secure communication with the ground base station (BS) is achieved. To achieve better performance, we formulate a multi-objective optimization problem for UAV network security communication (SCMOP), and jointly optimize the positions and excitation current weights of UAVs to set the null values in the direction of known eavesdroppers, reduce the sidelobe levels (SLLs) and enhance the directivity of the main lobe (ML). Since the formulated SCMOP is an NP-hard problem, we propose an improved the third non-dominated sorting genetic algorithm (IMNSGA-III) with chaos operator and crossover and mutation operators to solve the problem in this paper. The simulation results show that the IMNSGA-III can solve the SCMOP well and obtain the best results compared with other benchmark algorithms.

关键词： Chaos Wireless communication Array signal processing Null value Collaboration Autonomous aerial vehicles Statistics

来源：评论

学校读者我要写书评

暂无评论

Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding

arXiv

引用

arXiv 2022年

作者： Liang, Shining Shou, Linjun Pei, Jian Gong, Ming Zuo, Wanli Zuo, Xianglin Jiang, Daxin College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering MOE China STCA Microsoft Department of Electrical & Computer Engineering Duke University United States

Despite the great success of spoken language understanding (SLU) in high-resource languages, it remains challenging in low-resource languages mainly due to the lack of labeled training data. The recent multilingual code-switching approach achieves better alignments of model representations across languages by constructing a mixed-language context in zero-shot cross-lingual SLU. However, current code-switching methods are limited to implicit alignment and disregard the inherent semantic structure in SLU, i.e., the hierarchical inclusion of utterances, slots, and words. In this paper, we propose to model the utterance-slot-word structure by a multi-level contrastive learning framework at the utterance, slot, and word levels to facilitate explicit alignment. Novel code-switching schemes are introduced to generate hard negative examples for our contrastive learning framework. Furthermore, we develop a label-aware joint model leveraging label semantics to enhance the implicit alignment and feed to contrastive learning. Our experimental results show that our proposed methods significantly improve the performance compared with the strong baselines on two zero-shot cross-lingual SLU benchmark datasets. © 2022, CC BY-NC-ND.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Vector Quantization: A Case Study on Robust Medical Semantic Segmentation

SSRN

引用

SSRN 2024年

作者： Lang, Yijun Liu, Pingping Zhao, Hongwei Zhou, Qiuzhan College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China School of Mechanical Science and Engineering Jilin University Changchun130025 China College of Communication Engineering Jilin University Changchun130022 China

Pixel-wise medical image segmentation is essential for accurate disease diagnosis and analysis. Although these models exhibit high accuracy and impressive performance, they often face issues of trustworthiness due to their sensitivity to minor perturbations in the original images, which can cause significant deviations in segmentation tasks. To address these challenges, we focus on enhancing both the accuracy and the robustness of these systems against adversarial perturbations. We introduce a robust projection-head that utilizes a non-parametric method, Vector Quantization Momentum (VQM), to increase the hypothesis margin in the input space and reduce disturbances in the feature space. Additionally, we propose a new loss function, Anchor-based Vector Quantization (AVQ), designed to achieve denser pixel-prototype embedding. Our evaluation, using two white-box adversarial attack algorithms across two datasets, demonstrates a defense improvement of up to 14.46%. © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Complementary knowledge Compilation Using the Hyper Extension Rule

引用

Chinese Journal of Electronics 2019年第2期28卷 259-265页

作者： NIU Dangdang LIU Lei LYU Shuai XU Yue College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University

We introduce the concept of Complementary formula(COMF), which is a new and non-equivalent way for knowledge compilation(KC). Based on the Hyper extension rule(HER) which is an expansion of Extension rule(ER), we design a compilation algorithm which can formula compile each Conjunctive normal form(CNF)formula to complementary Fully complementary connected diagram(c-FCCD), named as C2C(CNF formula to cFCCD). Theoretically, c-FCCD is a kind of complementary formulae of the input formulae and can support all queries and partial transformations in KC map. Experimentally,C2C is competitive with the EPCCL compilers KCER,C2E, UKCHER, DKCHER and IKCHER.

关键词： knowledge compilation Extension rule Hyper extension rule Compilation language Each pair contains complementary literals(EPCCL) theory

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：