检索结果-内蒙古大学图书馆

MyWAL:performance optimization by removing redundant input/output stack in key-value store

Frontiers of Information Technology & Electronic engineering 2023年第7期24卷 980-993页

作者： Xiao ZHANG Mengyu LI Michael NGULUBE Yonghao CHEN Yiping ZHAO School of Computer Science Northwestern Polytechnical UniversityXi'an 710072China MIIT Key Laboratory of Big Data Storage and Management Northwestern Polytechnical UniversityXi'an 710072China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical UniversityXi'an 710072China School of Software Northwestern Polytechnical UniversityXi'an 710072China

Based on a log-structured merge(LSM)tree,the key-value(KV)storage system can provide high reading performance and optimize random writing *** is widely used in modern data storage systems like e-commerce,online analytics,and real-time *** LSM tree stores new KV data in the memory and flushes to disk in *** prevent data loss in memory if there is an unexpected crash,RocksDB appends updating data in the write-ahead log(WAL)before updating the ***,synchronous WAL significantly reduces writing *** this paper,we present a new WAL mechanism named *** directly manages raw devices(or partitions)instead of saving data on a traditional file *** can avoid useless metadata updating and write data sequentially on *** results show that MyWAL can significantly improve the data writing performance of RocksDB compared to the traditional WAL for small KV data on solid-state disks(SSDs),as much as five to eight times *** non-volatile memory express soild-state drives(NVMe SSDs)and non-volatile memory(NVM),MyWAL can improve data writing performance by 10%–30%.Furthermore,the results of YCSB(Yahoo!Cloud Serving Benchmark)show that the latency decreased by 50%compared with SpanDB.

关键词： Key-value(KV)store Log-structured merge(LSM)tree Non-volatile memory(NVM) Non-volatile memory express soild-state drive(NVMe SSD) Write-ahead log(WAL)

来源：评论

学校读者我要写书评

暂无评论

Mamba-DTA: Drug-Target Binding Affinity Prediction with State Space Model

Mamba-DTA: Drug-Target Binding Affinity Prediction with Stat...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yulong Wu Jin Xie Jing Nie Xiaohong Zhang Yuansong Zeng School of Big Data and Software Engineering Chongqing University China School of School of Microelectronics and Communication Engineering Chongqing University China Shanghai Artificial Intelligence Laboratory China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Biochemical methods for measuring drug-target binding are costly and slow, while deep learning offers a crucial solution. Deep learning methods for predicting drug-target binding affinity have achieved remarkable success, but existing approaches face challenges: adjacent elements in a three-dimensional structure may be far apart in a one-dimensional representation, and long sequences of drug and target data often contain lots of noise. In this paper, we introduce MambaDTA, a novel architecture for drug-target affinity prediction based on the State Space Model (SSM). Mamba-DTA utilizes SSM to model the drug molecules and target molecules and extract more discriminative spatial structural features efficiently and stably. Additionally, we design Interaction-based Selective Filtering (ISF) module to model drug-target interactions and filter out redundant information. The experimental results on two publicly available datasets, namely Davis and KIBA, demonstrate the effectiveness and superiority of our Mamba-DTA. Specifically, Mamba-DTA achieves a relative gain of 13.3% in terms of MAE on the Davis dataset. Source codes are available at https://***/202324131016T/Mamba-DTA.

关键词： Drugs Deep learning Source coding Biological system modeling Noise Predictive models Feature extraction Information filters Bioinformatics Faces

来源：评论

学校读者我要写书评

暂无评论

HGDRec:Next POI Recommendation Based on Hypergraph Neural Network and Diffusion Model

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1445-1458页

作者： Yinchen Pan Jun Zeng Ziwei Wang Haoran Tang Junhao Wen Min Gao School of Big Data and software engineering Chongqing University Chongqing China College of Computer Science and Technology Zhejiang University Hangzhou China Department of Computing The Hong Kong Polytechnic University Kowloon Hong Kong

In recent years, next Point-of-Interest (POI) recommendation is essential for many location-based services, aiming to predict the most likely POI a user will visit next. Current research employs graph-based and sequential methods, which have significantly improved performance. However, there are still limitations: numerous methods overlook the fact that user intent is constantly changing and complex. Furthermore, prior studies have seldom addressed spatiotemporal correlations while considering differences in user behavior patterns. Additionally, implicit feedback contains noise. To address these issues, we propose a recommender model named HGDRec for the next POI recommendation. Specifically, we introduce an approach for extracting trajectory intent by integrating multi-dimensional trajectory representations to achieve a multi-level understanding of user trajectories. Then, by analyzing users’ long trajectories, we construct global hypergraph structures across spatiotemporal regions to comprehensively capture user behavior patterns. Additionally, to further optimize trajectory intent representation, we employ a feature optimization method based on the improved diffusion model. Extensive experiments on three real-world datasets validate the superiority of HGDRec over the state-of-the-art methods.

关键词： Trajectory Diffusion models Spatiotemporal phenomena Feature extraction Optimization Transformers data mining Noise measurement data models Correlation

来源：评论

学校读者我要写书评

暂无评论

PAIR: protein-aptamer interaction prediction based on language models and contrastive learning framework

PAIR: protein-aptamer interaction prediction based on langua...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jun Zhang Zhiqiang Yan Hao Zeng Zexuan Zhu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Aptamers are single-stranded DNA or RNA oligonucleotides that selectively bind to specific targets, making them valuable for drug design and diagnostic applications. Identifying the interactions between aptamers and target proteins is crucial for these applications. The systematic evolution of ligands by exponential enrichment process, traditionally used for this purpose, is challenging and time-consuming. The resulting aptamers often suffer from limitations in stability and diversity. Computational approaches have shown promise in aiding the discovery of high-performance aptamers, but existing methods are usually constrained by insufficient training data and limited generalizability. Recently, advancements in pre-training large language models have offered a new avenue to mitigate the dependency on large datasets. In this study, we propose a novel method to predict aptamer-protein interactions using large language models within a contrastive learning framework. Experimental results demonstrate that our method exhibits superior generalization and outperforms existing approaches. This method holds promise as a powerful tool for predicting aptamer-protein interactions.

关键词： Proteins Drugs Protein engineering Biological system modeling Large language models Computational modeling Training data Contrastive learning Predictive models Few shot learning

来源：评论

学校读者我要写书评

暂无评论

VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting

arXiv

引用

arXiv 2024年

作者： Yang, Yingnan Zhu, Qingling Chen, Jianyong College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Multivariate time series (MTS) forecasting has been extensively applied across diverse domains, such as weather prediction and energy consumption. However, current studies still rely on the vanilla point-wise self-attention mechanism to capture cross-variable dependencies, which is inadequate in extracting the intricate cross-correlation implied between variables. To fill this gap, we propose Variable Correlation Transformer (VCformer), which utilizes Variable Correlation Attention (VCA) module to mine the correlations among variables. Specifically, based on the stochastic process theory, VCA calculates and integrates the cross-correlation scores corresponding to different lags between queries and keys, thereby enhancing its ability to uncover multivariate relationships. Additionally, inspired by Koopman dynamics theory, we also develop Koopman Temporal Detector (KTD) to better address the non-stationarity in time series. The two key components enable VCformer to extract both multivariate correlations and temporal dependencies. Our extensive experiments on eight real-world datasets demonstrate the effectiveness of VCformer, achieving top-tier performance compared to other state-of-the-art baseline models. Code is available at this repository: https://***/CSyyn/VCformer. Copyright © 2024, The Authors. All rights reserved.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Breaking the Clusters: Uniformity-Optimization for Text-Based Sequential Recommendation

arXiv

引用

arXiv 2025年

作者： Chen, Wuhan Wang, Zongwei Gao, Min Xia, Xin Jiang, Feng Wen, Junhao Ministry of Education Chongqing401331 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China The University of Queensland QLD4072 Australia

Traditional sequential recommendation (SR) methods heavily rely on explicit item IDs to capture user preferences over time. This introduces critical limitations in cold-start scenarios and domain transfer tasks, where unseen items and new contexts often lack established ID mappings. To overcome these limitations, recent studies have shifted towards leveraging text-only information for recommendation, thereby improving model generalization and adaptability across domains. Although promising, text-based SR faces unique difficulties: items’ text descriptions often share semantic similarities that lead to clustered item representations, compromising their uniformity, a property essential for promoting diversity and enhancing generalization in recommendation systems. In this paper, we explore a novel framework to improve the uniformity of item representations in text-based SR. Our analysis reveals that items within a sequence exhibit marked semantic similarity, meaning they are closer in representation than items overall, and that this effect is more pronounced for less popular items, which form tighter clusters compared to their more popular counterparts. Based on these findings, we propose UniT, a framework that employs three pairwise item sampling strategies: Unified General Sampling Strategy, Sequence-Driven Sampling Strategy, and Popularity-Driven Sampling Strategy. Each strategy applies varying degrees of repulsion to selectively adjust the distances between item pairs, thereby refining representation uniformity while considering both sequence context and item popularity. Extensive experiments on multiple real-world datasets demonstrate that our proposed approach consistently outperforms state-of-the-art models, validating the effectiveness of UniT in enhancing both representation uniformity and recommendation accuracy. The source code is available at https://***/ccwwhhh/Model-Rec. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Intelligent Blocking and Prevention of SARS-CoV-2 Based on Evolutionary Reinforcement Learning

Intelligent Blocking and Prevention of SARS-CoV-2 Based on E...

引用

Congress on Evolutionary Computation

作者： Chengwei He Huaping Hong Lijia Ma Qingling Zhu Yuan Bai College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

In recent years, the global repercussions of SARS-CoV-2 and its variants have posed significant challenges to various areas, including the economic order, transportation, healthcare, and education, and the mitigation and prevention of SARS-CoV-2 and other infectious diseases have received much attention. This paper tries to develop a rational and effective intervention strategy in response to the dynamic evolution of the SARS-CoV-2 epidemic. To address this issue, we first use the SEIR model to analyze the population distribution under the SARS-CoV-2 epidemic, and then integrate a deep Q-neural network (DQN) to reflect an economic quantification model contextualized within the SARS-CoV-2 scenario. Next, we propose an evolutionary deep reinforcement learning to generate an optimal and adaptive intervention strategy, by optimizing the weight sequence of the DQN. The experimental results show the effectiveness of the proposed method in maximizing economic benefits, while ensuring the uninterrupted functionality of medical institutions. Importantly, the learned intervention strategy exhibits the applicability to other infectious diseases.

关键词： Economics Epidemics Infectious diseases Prevention and mitigation Heuristic algorithms Sociology Loss measurement

来源：评论

学校读者我要写书评

暂无评论

MLRNet: Towards Real-Time Crowd Counting With Mobile-Based Lightweight Framework

MLRNet: Towards Real-Time Crowd Counting With Mobile-Based L...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Peirong Ji Xiaofeng Xia Zhiwei Wu Fusen Wang Xinyue Liu Jun Sang School of Big Data & Software Engineering Chongqing University Chongqing China

The trade-off between efficiency and generalization has been a challenging problem in crowd counting. In this work, we are devoted to suggesting an application-oriented solution to practical device deployment for crowd counting in resource-constrained scenes. In order to optimize the application computation complexity, this paper proposes a counting architecture, called Mobile Lightweight Refine Net (MLRNet), which is targeted for the high-effectiveness of neural networks in real-time crowd counting tasks on light-scale servers or intelligent devices. In the proposed framework, MobileNetV3 is used as the front-end which enables the model of an efficient feature extraction ability with low resource use. Besides, the back-end introduces the design of Light-weight RefineNet, which maintains the overall counting accuracy while compressing the computing costs. Extensive experiments on four mainstream datasets have demonstrated the availability of our proposed network. Particularly, compared with the baseline method, MLRNet achieves higher accuracy while only using around 1/3 of the FLOPS and parameters on three public crowd counting datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploration of engineering Practice Teaching Guided by Design Thinking 22

Exploration of Engineering Practice Teaching Guided by Desig...

引用

6th International Conference on Education and Multimedia Technology, ICEMT 2022

作者： Xu, Ke Cai, Yi School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education Guangzhou China

ISBN: (纸本)9781450396455

As a cutting-edge innovative method and tool, Design Thinking has effectively promoted many changes in global business, social and education fields in recent years. This work briefly introduces Design Thinking and related teaching reform, and then summarizes two problems in existing engineering practice teaching. In view of these problems, this work introduces Design Thinking into engineering practice teaching. As its core, Design Thinking Workshops are well designated and organized. Two-semesters explorations show that under the guidance of Design Thinking, engineering practice teaching is more attractive and effective. It can not only help engineering students learn to empathize with end-users and cultivate innovative thinking, but also improve their ability to identify and address real problems. © 2022 ACM.

关键词： engineering education

来源：评论

学校读者我要写书评

暂无评论

Generalizing Personalized Federated Graph Augmentation via Min-max Adversarial Learning 25

Generalizing Personalized Federated Graph Augmentation via M...

引用

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and data Mining V.1

作者： Liang Zhang Tao Long Yang Liu Lei Zhang Laizhong Cui Qingjiang Shi Shenzhen Research Institute of Big Data Shenzhen Guangdong China College of Computer Science and Software Engineering Shenzhen University Shenzhen Guangdong China Data Science Research Center Dukekunshan University Kunshan Jiangsu China School of Software Engineering Tongji University Yangpu Shanghai China

ISBN: (纸本)9798400712456

Federated learning (FL) enables the training of a global machine learning model among multiple local clients in a collaborative fashion without directly sharing the details of their data. Due to this advantage, it has been utilized in a wide range of applications where privacy is a critical concern and has attracted great attention for graph representation learning (GRL). Despite the offered advances, there still exist two major challenges in the FL for GRL across distributed graph data, including heterogeneity and complementarity. In order to tackle these challenges, a novel personalized federated graph augmentation (PFGA) framework is proposed in this work. Unlike existing techniques, it utilizes generative models as bridges to enable information sharing among clients, thereby facilitating the collaborative training of GRL models. Instead of directly using the generative model trained on each client individually, we aggregate them into the globally generative model to gain a global view of the entire graph, which effectively alleviates the heterogeneity and complementarity issues simultaneously. We formulate the training of the generative and GRL models as a min-max adversarial learning problem and theoretically prove the convergence. Furthermore, the effectiveness of the method is demonstrated using experimental results on six real-world datasets.

关键词： federated learning

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：