检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Chuyang Liu, Zhongxin Ren, Xiaoxue Zhang, Gehao Liang, Ming Lo, David State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou310027 China Ant Group China School of Computing and Information Systems Singapore Management University 188065 Singapore

Fault localization (FL) targets identifying bug locations within a software system, which can enhance debugging efficiency and improve software quality. Due to the impressive code comprehension ability of Large Language Models (LLMs), a few studies have proposed to leverage LLMs to locate bugs, i.e., LLM-based FL, and demonstrated promising performance. However, first, these methods are limited in flexibility. They rely on bug-triggering test cases to perform FL and cannot make use of other available bug-related information, e.g., bug reports. Second, they are built upon proprietary LLMs, which are, although powerful, confronted with risks in data privacy. To address these limitations, we propose a novel LLM-based FL framework named FlexFL, which can flexibly leverage different types of bug-related information and effectively work with open-source LLMs. FlexFL is composed of two stages. In the first stage, FlexFL reduces the search space of buggy code using state-of-the-art FL techniques of different families and provides a candidate list of bug-related methods. In the second stage, FlexFL leverages LLMs to delve deeper to double-check the code snippets of methods suggested by the first stage and refine fault localization results. In each stage, FlexFL constructs agents based on open-source LLMs, which share the same pipeline that does not postulate any type of bug-related information and can interact with function calls without the out-of-the-box capability. Extensive experimental results on Defects4J demonstrate that FlexFL outperforms the baselines and can work with different open-source LLMs. Specifically, FlexFL with a lightweight open-source LLM Llama3-8B can locate 42 and 63 more bugs than two state-of-the-art LLM-based FL approaches AutoFL and AgentFL that both use GPT-3.5. In addition, FlexFL can localize 93 bugs that cannot be localized by non-LLM-based FL techniques at the top 1. Furthermore, to mitigate potential data contamination, we conduct experiment

关键词： Program debugging

来源：评论

学校读者我要写书评

暂无评论

Federated graph learning for cross-domain recommendation 24

Federated graph learning for cross-domain recommendation

引用

Proceedings of the 38th International Conference on Neural information Processing systems

作者： Ziqi Yang Zhaopeng Peng Zihui Wang Jianzhong Qi Chaochao Chen Weike Pan Chenglu Wen Cheng Wang Xiaoliang Fan Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University China and Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Computing and Information Systems The University of Melbourne Australia College of Computer Science and Technology Zhejiang University Hangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798331314385

Cross-domain recommendation (CDR) offers a promising solution to the data sparsity problem by enabling knowledge transfer between source and target domains. However, many recent CDR models overlook crucial issues such as privacy as well as the risk of negative transfer (which negatively impact model performance), especially in multi-domain settings. To address these challenges, we propose FedGCDR, a novel federated graph learning framework that securely and effectively leverages positive knowledge from multiple source domains. First, we design a positive knowledge transfer module that ensures privacy during inter-domain knowledge transmission. This module employs differential privacy-based knowledge extraction combined with a feature mapping mechanism, transforming source domain embeddings from federated graph attention networks into reliable domain knowledge. Second, we design a knowledge activation module to filter out potential harmful or conflicting knowledge from source domains, addressing the issues of negative transfer. This module enhances target domain training by expanding the graph of the target domain to generate reliable domain attentions and fine-tunes the target model for improved negative knowledge filtering and more accurate predictions. We conduct extensive experiments on 16 popular domains of the Amazon dataset, demonstrating that FedGCDR significantly outperforms state-of-the-art methods. We open source the code at https://***/LafinHana/FedGCDR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

tSS-BO: Scalable Bayesian Optimization for Analog Circuit Sizing via Truncated Subspace Sampling

tSS-BO: Scalable Bayesian Optimization for Analog Circuit Si...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Tianchen Gu Jiaqi Wang Zhaori Bi Changhao Yan Fan Yang Yajie Qin Tao Cui Xuan Zeng State Key Laboratory of Integrated Chips and Systems School of Microelectronics Fudan University Shanghai China State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences & University of Chinese Academy of Sciences Beijing China State Key Laboratory of Integrated Chips and Systems School of Information Science and Technology Fudan University Shanghai China

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

We propose a novel scalable Bayesian optimization method with truncated subspace sampling (tSS-BO) to tackle high-dimensional optimization challenges for large-scale analog circuit sizing. To address the high-dimensional challenges, we propose subspace sampling subject to a truncated Gaussian distribution. This approach limits the effective sampling dimensionality down to a constant upper bound, independent of the original dimensionality, leading to a significant reduction in complexity associated with the curse of dimensionality. The distribution covariance is iteratively updated using a truncated flow, where approximate gradients and center steps are integrated with decaying prior subspace features. We introduce gradient sketching and local Gaussian process (GP) models to approximate gradients without additional simulations to mitigate systematic errors. To enhance efficiency and ensure compatibility with constraints, we utilize local GP models for the selection of promising candidates, avoiding the cost of acquisition function optimization. The proposed tSS-BO method exhibits clear advantages over state-of-the-art methods in experimental comparisons. In synthetic benchmark functions, the tSS-BO method achieves up to $4.93\times$ evaluation speedups and a remarkable over $30\times$ algorithm complexity reduction compared to the Bayesian baseline. In real-world analog circuits, our method achieves up to $2\times$ speedups in simulation number and runtime.

关键词： Adaptation models Upper bound Runtime Systematics Optimization methods Gaussian processes Analog circuits

来源：评论

学校读者我要写书评

暂无评论

Improving accuracy-robustness trade-off via pixel reweighted adversarial training 24

Improving accuracy-robustness trade-off via pixel reweighted...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Jiacheng Zhang Feng Liu Dawei Zhou Jingfeng Zhang Tongliang Liu School of Computing and Information Systems The University of Melbourne State Key Laboratory of Integrated Services Networks Xidian University School of Computer Science The University of Auckland / RIKEN AIP Sydney AI Centre The University of Sydney

Adversarial training (AT) trains models using adversarial examples (AEs), which are natural images modified with specific perturbations to mislead the model. These perturbations are constrained by a predefined perturbation budget ε and are equally applied to each pixel within an image. However, in this paper, we discover that not all pixels contribute equally to the accuracy on AEs (i.e., robustness) and accuracy on natural images (i.e., accuracy). Motivated by this finding, we propose Pixel-reweighted AdveRsarial Training (PART), a new framework that partially reduces ε for less influential pixels, guiding the model to focus more on key regions that affect its outputs. Specifically, we first use class activation mapping (CAM) methods to identify important pixel regions, then we keep the perturbation budget for these regions while lowering it for the remaining regions when generating AEs. In the end, we use these pixel-reweighted AEs to train a model. PART achieves a notable improvement in accuracy without compromising robustness on CIFAR-10, SVHN and TinyImagenet-200, justifying the necessity to allocate distinct weights to different pixel regions in robust classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DAANet: Dual Attention Aggregating Network for Salient Object Detection

DAANet: Dual Attention Aggregating Network for Salient Objec...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Li, Yijie Wang, Hewei Li, Zhenqi Wang, Shaofan Dev, Soumyabrata Zuo, Guoyu Beijing University of Technology Beijing-Dublin International College Beijing100124 China Beijing University of Technology Faculty of Information Technology Beijing100124 China University College Dublin School of Computer Science Dublin Ireland Beijing University of Technology Faculty of Information Technology China Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China

ISBN: (纸本)9798350325706

When the Convolutional neural network (CNN) has been introduced for computer vision, many researches use CNN-based model to perform salient object detection (SOD). In recent years, The feature pyramid network (FPN) based structure is more popular for salient object detection tasks. In this paper, to improve the overall performance of salient object detection tasks, we propose a dual attention aggregating network (DAANet), which is an FPN-based deep convolutional neural network with a dual attention aggregation module (DAAM) and dilated refinement block (DRB). The DRB module uses convolutions with different dilation rates to expand the receptive field. The DAAM considers the salient map prediction from the low-level output as pseudo-attention which can efficiently aggregate multi-scale information. The convolution block attention module (CBAM) in DAAM can refine the aggregation of pseudo-attention which enables better performance. We evaluate DAANet on six benchmark datasets that prove the effectiveness of DAANet and its components. Our implementation can be found at: https://***/Att100/DAANet. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of OOP-Related Bugs in C++ Compilers

引用

IEEE Transactions on Software Engineering 2025年 1-21页

作者： Wang, Bo Chen, Chong Chen, Junjie Xu, Bowen Ye, Chen Lin, Youfang Dong, Guoliang Sun, Jun Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence China Tianjin University College of Intelligence and Computing Tianjin300350 China North Carolina State University Department of Computer Science NC27695 United States Singapore Management University School of Computing and Information Systems Singapore178902 Singapore

Modern C++, a programming language characterized by its extensive use of object-oriented programming (OOP) features, is widely used for system programming. However, C++ compilers often struggle to correctly handle these sophisticated OOP features, resulting in numerous high-profile compiler bugs that can lead to crashes or miscompilation. Despite the significance of OOP-related bugs, existing studies largely overlook OOP features, hindering their ability to discover such bugs. To assist both compiler fuzzer designers and compiler developers, we conduct a comprehensive study of the compiler bugs caused by incorrectly handling C++ OOP-related features. First, we systematically extract 788 OOP-related C++ compiler bugs from GCC and LLVM. Second, derived from the core concepts of OOP and C++, we manually identified a two-level taxonomy of the OOP-related features leading to compiler bugs, which consists of 6 primary categories (e.g., Abstraction & Encapsulation, Inheritance, and Runtime Polymorphism), along with 17 secondary categories (e.g., Constructors & Destructors and Multiple Inheritance). Third, we systematically analyze the root causes, symptoms, fixes, options, and C++ standard versions of these bugs. Our analysis yields 13 key findings, highlighting that features related to the construction and destruction of objects lead to the highest number of bugs, crashes are the most frequent symptom, and while the average time from bug introduction to discovery is 1856 days, fixing the bug once discovered takes only 174 days on average. Additionally, more than half of the bugs can be triggered without any compiler options. These findings offer valuable insights not only for developing new compiler testing approaches but also for improving language design and compiler engineering. Inspired by these findings, we developed a proof-of-concept compiler fuzzer OOPFuzz, specifically targeting OOP-related bugs in C++ compilers. We applied it against the newest release versions

关键词： C++ (programming language)

来源：评论

学校读者我要写书评

暂无评论

Semantic Heads Segmentation and Counting in Crowded Retail Environment with Convolutional Neural Networks Using Top View Depth Images

引用

SN Computer Science 2023年第1期4卷 61页

作者： Abed, Almustafa Akrout, Belhassen Amous, Ikram Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Alkharj 11942 Saudi Arabia Multimedia Information Systems and Advanced Computing Laboratory (MIRACL) Sfax University Sfax 3021 Tunisia ENET’COM University of Sfax National School of Electronics and Telecommunications of Sfax Road Tunis City El Ons Sfax 3018 Tunisia

In recent years, researchers have developed several techniques to accurately count the number of people in a crowded retail environment for human behavior analysis, ranging from vision and feature based approaches to machine-learning and deep learning approaches. Due to the availability and affordability of recent advanced technologies such as depth sensors and high computing powers as well as the availability of big data, the need for building accurate models to detect and count people in crowded environments arises. Deep learning approaches has proven to be highly accurate especially when there is enough data to train the model and high computation powers. People detection and counting is a challenging problem. due to several issues such as occlusion, light variations, complex backgrounds to name a few. To cope with these issues, we utilize a top-view configuration depth data to train our model. We propose a convolutional encoder decoder architecture consisting of a resnet50 encoder trained on the ImageNet dataset as a transfer learning technique and we built the decoder part of the model as a novel contribution, for segmenting and counting customers heads in a crowded retail stores where there are more than 6 individuals per square meter without compromising people privacy because the camera does not record people’s faces. The objective of our method is to segment and count people using the publicly available TV-Head Dataset and People Counting DataSet (PCDS). The results demonstrate that our model is robust and can be used for real time people counting with accurate results. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Computer vision Convolutional neural networks Intelligent retail environment People counting Top-view configuration

来源：评论

学校读者我要写书评

暂无评论

RIGID: Recurrent GAN Inversion and Editing of Real Face Videos

arXiv

引用

arXiv 2023年

作者： Xu, Yangyang He, Shengfeng Wong, Kwan-Yee K. Luo, Ping Deapartment of Computer Science The University of Hong Kong Hong Kong School of Computing and Information Systems Singapore Management University Singapore Shanghai AI Laboratory China

GAN inversion is indispensable for applying the powerful editability of GAN to real images. However, existing methods invert video frames individually often leading to undesired inconsistent results over time. In this paper, we propose a unified recurrent framework, named Recurrent vIdeo GAN Inversion and eDiting (RIGID), to explicitly and simultaneously enforce temporally coherent GAN inversion and facial editing of real videos. Our approach models the temporal relations between current and previous frames from three aspects. To enable a faithful real video reconstruction, we first maximize the inversion fidelity and consistency by learning a temporal compensated latent code. Second, we observe incoherent noises lie in the high-frequency domain that can be disentangled from the latent space. Third, to remove the inconsistency after attribute manipulation, we propose an in-between frame composition constraint such that the arbitrary frame must be a direct composite of its neighboring frames. Our unified framework learns the inherent coherence between input frames in an end-to-end manner, and therefore it is agnostic to a specific attribute and can be applied to arbitrary editing of the same video without re-training. Extensive experiments demonstrate that RIGID outperforms state-of-the-art methods qualitatively and quantitatively in both inversion and editing tasks. The deliverables can be found in https://***/RIGID. © 2023, CC BY-NC-ND.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Sustainability Forecasting for Deep Learning Packages

Sustainability Forecasting for Deep Learning Packages

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Junxiao Han Yunkun Wang Zhongxin Liu Lingfeng Bao Jiakun Liu David Lo Shuiguang Deng School of Computer & Computing Science Hangzhou City University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Computing and Information Systems Singapore Management University Singapore Singapore

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

Deep Learning (DL) technologies have been widely adopted to tackle various tasks. In this process, through software dependencies, a multi-layer DL supply chain (SC) is formed, with DL frameworks acting as the root, DL packages acting as the bridge nodes, and downstream DL projects acting as the periphery. However, most Open Source Software (OSS) projects may fail. Considering the crucial position of DL packages in the DL SC, to foster the sustainable development of DL SCs and DL packages, we aim to forecast the long-term sustainability of DL packages. Here, sustained activity is adopted as the main proxy of sustainability, and the sustainability status is classified as “sus-tainable” or “dormant”. Relatedly, a DL package is considered as “sustainable” if it has sustained activity in its last 12 months. Otherwise, it is deemed as “dormant”. To this end, we propose an approach that begins with obtaining longitudinal features for each DL package in each month. Then, we develop a model to forecast the sustainability of DL packages by incorporating the longitudinal features, which can aptly predict sustainability with an accuracy of up to 0.81. Subsequently, an interpretable module is developed to interpret the determinants (i.e., important features) that impact the sustainability of DL packages. Finally, we generate sustainability trajectories for each DL package to better understand the monthly changes of their sustainability status. Our findings uncover that for most DL packages, fewer but more centralized developers and a balanced collaboration are more likely to help sustain the DL packages. Furthermore, although some DL packages are sustainable, their sustainability trajectories present statistically decreasing trends over time. Based on the findings, we shed light on the dynamic sustainability of DL packages, highlight future research directions, and provide practical suggestions to DL package maintainers, developers, users, and software engineering researchers.

关键词： Deep learning Supply chains Predictive models Market research Trajectory Sustainable development Task analysis

来源：评论

学校读者我要写书评

暂无评论

FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting

arXiv

引用

arXiv 2025年

作者： Zhu, Huilin Yuan, Jingling Yang, Zhengwei Guo, Yu Zhong, Xian He, Shengfeng Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China School of Computing and Information Systems Singapore Management University Singapore School of Computer Science Wuhan University China School of Navigation Wuhan University of Technology China

In class-agnostic object counting, the goal is to estimate the total number of object instances in an image without distinguishing between specific categories. Existing methods often predict this count without considering class-specific outputs, leading to inaccuracies when such outputs are required. These inaccuracies stem from two key challenges: 1) the prevalence of single-category images in datasets, which leads models to generalize specific categories as representative of all objects, and 2) the use of mean squared error loss during training, which applies uniform penalization. This uniform penalty disregards errors in less frequent categories, particularly when these errors contribute minimally to the overall loss. To address these issues, we propose FocalCount, a novel approach that leverages diverse feature attributes to estimate the number of object categories in an image. This estimate serves as a weighted factor to correct class-count imbalances. Additionally, we introduce Focal-MSE, a new loss function that integrates binary cross-entropy to generate stronger error gradients, enhancing the model’s sensitivity to errors in underrepresented categories. Our approach significantly improves the model’s ability to distinguish between specific classes and general counts, demonstrating superior performance and scalability in both few-shot and zero-shot scenarios across three object counting datasets. The code will be released soon. © 2025, CC BY.

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：