检索结果-内蒙古大学图书馆

33rd ACM Web Conference, WWW 2024

作者： Chen, Junfan Zhang, Richong Wang, Jiarui Hu, Chunming Mao, Yongyi SKLSDE School of Software Beihang University Beijing China SKLSDE School of Computer Science Beihang University Beijing China School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

ISBN: (纸本)9798400701719

Text classification is one vital tool assisting web content mining. Semi-supervised text classification (SSTC) offers an approach to alleviate the burden of annotation costs by training on a few labeled texts alongside many unlabeled texts. Unsolved challenges in SSTC are the overfitting problem caused by the limited labeled data and the mislabeling problem of unlabeled texts. To address these issues, this paper proposes a Self-Paced PairWise representation learning (SPPW) model. Concretely, SPPW alleviates the overfitting problem by replacing the overfitting-prone learning of a parameterized classifier with representation learning in a pair-wise manner. Besides, we propose a novel self-paced text filtering method that effectively integrates both label confidence and text hardness to reduce mislabeled texts synergistically. Extensive experiments on 3 benchmark SSTC datasets show that SPPW outperforms baselines and is effective in mitigating overfitting and mislabeling problems. © 2024 ACM.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A survey of Detecting Flakiness in Automated Test Regression Suite 21

A survey of Detecting Flakiness in Automated Test Regression...

引用

21st International Learning and Technology Conference, L and T 2024

作者： Elgazzar, Mohamed Hossny, Eman Omara, Fatma A. Faculty of Computers and Informaiton Software Engineering Dept Cairo Egypt Faculty of Computers and Informaiton Computer Science Dept Cairo Egypt

ISBN: (纸本)9798350393569

Recently, Flaky Tests have gotten the attention of the research community. These tests not only waste time and resources, but also undermine the reliability of the automated tests and hence the software systems are affected. So, the detection of Flaky Tests is very important and has a wide audience from both industry and academia. In addition, the research work is very promising having a great potential for the contribution that maps to a true value added to the up-to-date industry projects. Although lots of effort has been done to detect Flakiness in the software systems, the majority of the existed works focuses on different techniques in isolation. The aim of the work in this paper is to overlook the existed flakiness detection techniques, try to analyze them, and hold a comparison, indicating the proper context for each one. Most of the existed flakiness detection techniques are done on unit tests and library/technical projects. According to the comparative study among these techniques, it is found gaps and wide potential for contribution. On the other hand, flakiness detection techniques can be clustered under three main headers;First, study the phenomena under different testing levels by trying to focus on projects with integration, system, and end-toend tests. Second, study the phenomena under different Project types and data sets by studying business projects with user interfaces and mobile applications and so on. Third, study the phenomena toward a faster delivery cycle by studying flake tests in the context of parallel execution and Continuous Integration and Continuous Deployment (CI/CD). We can conclude that not all detection techniques have the same potential where some techniques are very competent while others still struggle to achieve considerable efficiency. © 2024 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Enhancing Code Generation for Dataflow Programming: Fine-Tuning Large Language Models with the DFCPP Dataset 22

Enhancing Code Generation for Dataflow Programming: Fine-Tun...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Luo, Qiuming Ma, Xi Wei, Xuan Shenzhen University College of Computer Science and Software Engineering Shenzhen China Tianjin Yuyi Kaihong Intelligent Technology Tianjin China

ISBN: (纸本)9798331509712

In recent years, large language models (LLMs) based on the Transformer architecture have demonstrated excellent performance in code generation, but there have been fewer studies on data flow languages. This study proposes a scheme for fine-tuning large language models based on the DFCPP dataset. We demonstrate the model's ability to generate dataflow graph (DAG) topologies and achieve significant performance improvements. Experimental results show that the BLEU score of the fine-tuned model in the DFCPP code generation task reaches 0.193, which is an increase of 112.1% compared to the non-fine-tuned model (0.091). This demonstrates the effectiveness of fine-tuning techniques in domain-specific code generation. © 2024 IEEE.

关键词： Data flow analysis

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Search Method for Accelerating Convolutional Neural Architecture Search 23

A Hybrid Search Method for Accelerating Convolutional Neural...

引用

15th International Conference on Machine Learning and Computing, ICMLC 2023

作者： Xun, Zhou Songbai, Liu Ka-Chun, Wong Qiuzhen, Lin Kaychen, Tan The Department of Computer Science City University of Hong Kong Hong Kong College of Computer Science and Software Engineering Shenzhen University KA-CHun Wong China College of Computer Science and Software Engineering Shenzhen University China The Department of Computing The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9781450398411

The performance evaluation of candidate architectures is a key step in evolution-based neural architecture search (ENAS). Generally, high-fidelity evaluation is desired for finding the optimal architecture but suffers from expensive computational cost while low-fidelity evaluation can reduce search cost but may influence the search performance. In this work, a hybrid search method, HybridNAS, is proposed by synergizing these two evaluation strategies to improve the search effectiveness of ENAS. This method consists of two stages: global exploration and local exploitation. The former applies low-fidelity evaluation to explore the promising architectures efficiently. As for the latter, it exploits the most promising ones identified by the former to generate the better-performancing architectures. Those two stages are iteratively repeated toward the optimal architecture. Extensive experiments on NAS-Bench-101 and NAS-Bench-201 reflect that HybridNAS can achieve comparable accuracy compared to existing popular NAS but at the expense of only 60%-80% computational cost. © 2023 ACM.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting 38

DDN: Dual-domain Dynamic Normalization for Non-stationary Ti...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dai, Tao Wu, Beiliang Liu, Peiyuan Li, Naiqi Yuerong, Xue Xia, Shu-Tao Zhu, Zexuan College of Computer Science and Software Engineering Shenzhen University China Tsinghua Shenzhen International Graduate School Tsinghua University China

Deep neural networks (DNNs) have recently achieved remarkable advancements in time series forecasting (TSF) due to their powerful ability of sequence dependence modeling. To date, existing DNN-based TSF methods still suffer from unreliable predictions for real-world data due to its non-stationarity characteristics, i.e., data distribution varies quickly over time. To mitigate this issue, several normalization methods (e.g., SAN) have recently been specifically designed by normalization in a fixed period/window in the time domain. However, these methods still struggle to capture distribution variations, due to the complex time patterns of time series in the time domain. Based on the fact that wavelet transform can decompose time series into a linear combination of different frequencies, which exhibits distribution variations with time-varying periods, we propose a novel Dual-domain Dynamic Normalization (DDN) to dynamically capture distribution variations in both time and frequency domains. Specifically, our DDN tries to eliminate the non-stationarity of time series via both frequency and time domain normalization in a sliding window way. Besides, our DDN can serve as a plug-in-play module, and thus can be easily incorporated into other forecasting models. Extensive experiments on public benchmark datasets under different forecasting models demonstrate the superiority of our DDN over other normalization methods. Code is available at https://***/Hank0626/DDN. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Building a domain-specific compiler for emerging processors with a reusable approach

引用

science China(Information sciences) 2024年第1期67卷 20-38页

作者： Mingzhen LI Yi LIU Bangduo CHEN Hailong YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University

High-performance computing and deep learning domains have been motivating the design of domain-specific *** these processors can provide promising computation capability,they are notorious for exotic programming *** improve programming productivity and fully exploit the performance potential of these processors,domain-specific compilers(DSCs) have been ***,building DSCs for emerging processors requires tremendous engineering efforts because the commonly used compilation stack is difficult to be *** to the advent of multilevel intermediate representation(MLIR),DSC developers can leverage reusable infrastructure to extend their customized functionalities without rebuilding the entire compilation *** this paper,we further demonstrate the effectiveness of MLIR by extending its reusable infrastructure to embrace a heterogeneous many-core processor(Sunway processor).In particular,we design a new Sunway dialect and corresponding backend for the Sunway processor,fully exploiting its architectural advantage and hiding its programming *** show the ease of building a DSC,we leverage the Sunway dialect and existing MLIR dialects to build a stencil compiler for the Sunway *** experimental results show that our stencil compiler,built with a reusable approach,can even perform better than state-of-the-art stencil compilers.

关键词： domain-specific compiler emerging processor reusable dialect performance optimization MLIR

来源：评论

学校读者我要写书评

暂无评论

Skin cancer detection with MobileNet-based transfer learning and MixNets for enhanced diagnosis

引用

Neural Computing and Applications 2024年第34期36卷 21383-21413页

作者： Zakariah, Mohammed Al-Razgan, Muna Alfakih, Taha Department of Computer Sciences and Engineering College of Applied Science King Saud University Riyadh11543 Saudi Arabia Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh11345 Saudi Arabia Department of Information Systems College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia

Skin cancer poses a significant health hazard, necessitating the utilization of advanced diagnostic methodologies to facilitate timely detection, owing to its escalating prevalence in recent years. This paper proposes a novel approach to tackle the issue by introducing a method for detecting skin cancer that uses MixNets to enhance diagnosis and leverages mobile network-based transfer learning. Skin cancer has diverse forms, each distinguishable by its structural attributes, morphological characteristics, texture, and coloration. The pressing demand for accurate and efficient diagnostic instruments has spurred the investigation of novel techniques. The present study utilizes the ISIC dataset, comprising a validation set of 660 images and a training set of 2637 images. Moreover, the research employs a combination of MixNets and mobile network-based transfer learning as its chosen approach. Transfer learning is a technique that leverages preexisting models to enhance the diagnostic capabilities of the proposed system. Integrating MobileNet and MixNets allows for utilizing their respective functionalities, resulting in a dual-model methodology that enhances the comprehensiveness of skin cancer diagnosis. The results demonstrate impressive performance metrics, with MobileNet and MixNets models, and the proposed approach achieves an outstanding accuracy rate of 99.58%. The above findings underscore the efficacy of the dual-model method in effectively discerning between benign and malignant skin lesions. Moreover, the present study aims to examine the potential integration of emerging technologies to enhance the accuracy and practicality of diagnostics within real-world healthcare settings. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Pre-Trained Language Models Represent Some Geographic Populations Better Than Others 30

Pre-Trained Language Models Represent Some Geographic Popula...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Dunn, Jonathan Adams, Benjamin Madabushi, Harish Tayyar University of Illinois Urbana-Champaign Department of Linguistics United States University of Canterbury Department of Computer Science and Software Engineering New Zealand University of Bath Department of Computer Science United Kingdom

ISBN: (纸本)9782493814104

This paper measures the skew in how well two families of LLMs represent diverse geographic populations. A spatial probing task is used with geo-referenced corpora to measure the degree to which pre-trained language models from the opt and bloom series represent diverse populations around the world. Results show that these models perform much better for some populations than others. In particular, populations across the US and the UK are represented quite well while those in South and Southeast Asia are poorly represented. Analysis shows that both families of models largely share the same skew across populations. At the same time, this skew cannot be fully explained by sociolinguistic factors, economic factors, or geographic factors. The basic conclusion from this analysis is that pre-trained models do not equally represent the world's population: there is a strong skew towards specific geographic populations. This finding challenges the idea that a single model can be used for all populations. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： geographic corpora population skew spatial probing under-represented populations

来源：评论

学校读者我要写书评

暂无评论

Application of Static Virus Spread Algorithm in Base-Balanced DNA Fragment Optimization

Application of Static Virus Spread Algorithm in Base-Balance...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Yao, Yao Zheng, Yanfen Zhang, Xun Liu, Xin Zhang, Xiaokang Wang, Bin Zhang, Qiang Dalian University of Technology School of Computer Science and Technology Dalian China Dalian University School of Software Engineering Dalian China

ISBN: (纸本)9798350386226

DNA has found applications in a diverse array of fields such as computing, medical diagnosis, and circuits. Designing DNA fragments that meet specific requirements is crucial for ensuring the smooth execution of tasks in these domains. However, the conventional approach of combining constraints with evolutionary algorithms often encounters challenges like orthogonality and thermodynamic instability. This poses risks to the control of reaction processes. To tackle these challenges, we have undertaken two tasks in this study: expanding constraint sets and innovating evolutionary algorithms. Firstly, we propose a base balance strategy aimed at enhancing the thermodynamic properties within DNA fragment groups by diversifying neighboring base combinations. The addition of this strategy achieves a minimum variance of 0.03 for the melting temperature while ensuring orthogonality. It represents a significant improvement compared to previous results and reduces the complexity of controlling reactions. Secondly, our static virus spread algorithm optimizes target DNA fragments by base mutations and virus amplification. Simultaneously,it demonstrates good performance across 23 benchmark functions, highlighting its optimization potential. This work is expected to further refine theoretical shortcomings and offer a convenient tool for DNA fragment optimization. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Towards 360∘ image compression for machines via modulating pixel significance

引用

Multimedia Tools and Applications 2024年第42期83卷 90271-90288页

作者： Zheng, Silin Shen, Xuelin Zhang, Qiudan Chen, Zhuo Yang, Wenhan Wang, Xu College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen51800 China Guangdong Shenzhen51800 China Peng Cheng Laboratory Guangdong Shenzhen51800 China

The rapid growth of computer vision-based applications, including smart cities and autonomous driving, has created a pressing demand for efficient 360∘ image compression and computer vision analytics. In most circumstances, 360∘ image compression and computer vision face challenges arising from the oversampling inherent in the Equirectangular Projection (ERP). However, these two fields often employ divergent technological approaches. Since image compression aims to reduce redundancy, computer vision analytics attempts to compensate for the semantic distortion caused by the projection process, resulting in a potential conflict between the two objectives. This paper explores a potential route, i.e.360∘ Image Coding for Machine (360-ICM), which offers an image processing framework that addresses both object deformation and oversampling redundancy within a unified framework. The key innovation lies in inferring a pixel-wise significant map by jointly considering the requirements of redundancy removal and object deformation offsetting. The significance map would be subsequently fed to a deformation-aware image compression network, guiding the bit allocation process as an external condition. More specifically, we employ a deformation-aware image compression network that is characterized by the Spatial Feature Transform (SFT) layer, which is capable of performing complex affine transformations of high-level semantic features, to be essential in dealing with the deformation. The image compression network and significance inference network are jointly trained under the supervision of a 360∘ image-specified object detection network, obtaining a compact representation that is both analytics-oriented and deformation-aware. Extensive experimental results have demonstrated the superiority of the proposed method over existing state-of-the-art image codecs in terms of rate-analytics performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part

关键词：

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：