检索结果-内蒙古大学图书馆

IEEE International Conference on Software Reliability Engineering Workshops (ISSRE Wksp)

作者： Shenglin Zhang Pengtian Zhu Minghua Ma Jiagang Wang Yongqian Sun Dongwen Li Jingyu Wang Qianying Guo Xiaolei Hua Lin Zhu Dan Pei Nankai University Haihe Laboratory of Information Technology Application Innovation Microsoft Tsinghua University Tianjin Key Laboratory of Software Experience and Human Computer Interaction China Mobile Research Institute Beijing National Research Center for Information Science and Technology

ISBN: (数字)9798350367041

ISBN: (纸本)9798350367058

Large language models (LLMs) excel at general question-answering (Q&A) but often fall short in specialized domains due to a lack of domain-specific knowledge. Commercial companies face the dual challenges of privacy protection and resource constraints when involving LLMs for fine-tuning. This paper propose a novel framework, Self-Evolution, designed to address these issues by leveraging lightweight open-source LLMs through multiple iterative fine-tuning rounds. To enhance the efficiency of iterative fine-tuning, Self-Evolution employ a strategy that filters and reinforces the knowledge with higher value during the iterative process. We employed Self-Evolution on Qwen1.5-7B-Chat using 4,000 documents containing rich domain knowledge from China Mobile, achieving a performance score 174% higher on domain-specific question-answering evaluations than Qwen1.5-7B-Chat and even 22% higher than Qwen1.5-72B-Chat. Self-Evolution has been deployed in China Mobile’s daily operation and maintenance for 117 days, and it improves the efficiency of locating alarms, fixing problems, and finding related reports, with an average efficiency improvement of over 18.6%. In addition, we release Self-Evolution framework code in https://***/Zero-Pointer/Self-Evolution.

关键词： Privacy Filters Large language models Conferences Software reliability Maintenance Iterative methods Data mining Protection Faces

来源：评论

学校读者我要写书评

暂无评论

Long and Recent Preference Learning with Recent-k Items Distribution for Recommender System

引用

IEEE Transactions on Multimedia 2025年

作者： Gao, Yongbiao Niu, Sijie Lv, Guohua Ling, Miaogen Geng, Xin Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China Southeast University Ministry of Education Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application China University of Jinan Shandong Provincial Key Laboratory of Ubiquitous Intelligent Computing School of Information Science and Engineering China Nanjing University of Information Science and Technology School of Computer Science China Southeast University School of Computer Science and Engineering China

Reinforcement learning (RL) aims to formulate the recommendation task as a Markov decision process (MDP) and trains an agent to automatically learn the optimal recommendation policy from interaction trajectories through trial-and-error and reward mechanisms. However, most existing RL-based approaches overlook the correlation between items and the dynamics of user interests implied in temporally close interactions. Therefore, in this paper, we propose a reinforcement learning method that incorporates a "recent-k items"distribution to capture users' local preferences. Specifically, we model the output layer as two distinct branches. The "recent-k items"branch, formulated with a Kullback-Leibler divergence loss, learns the recent interests of users, whereas the other branch utilizes a one-step temporal difference error to capture long-term preferences. The proposed structure is integrated into deep Q-learning and actor-critics, resulting in two enhanced methods named R k Q and R k AC, respectively. Furthermore, a novel soft inter-reward is carefully designed to enhance the proposed method, and we theoretically prove the convergence of the proposed algorithm. We perform extensive experiments on two large real-world datasets and conduct further analysis of the influences of different action sequences, time intervals, and enhancement capabilities for state-of-the-art models. The experimental results demonstrate the efficacy of our proposed methods. © 1999-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing

arXiv

引用

arXiv 2024年

作者： He, Liyang Chen, Enhong Huang, Zhenya Wang, Fei Wang, Shijin Liu, Jiayu Sha, Jing School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China State Key Laboratory of Cognitive Intelligence Hefei China School of Data Science University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China iFLYTEK AI Research State Key Laboratory of Cognitive Intelligence Hefei China

Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale backbones (e.g., ViT) in unsupervised semantic hashing models can yield substantial improvements. However, the inference delay has become increasingly difficult to overlook. Knowledge distillation provides a means for practical model compression to alleviate this delay. Nevertheless, the prevailing knowledge distillation approaches are not explicitly designed for semantic hashing. They ignore the unique search paradigm of semantic hashing, the inherent necessities of the distillation process, and the property of hash codes. In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models. To ensure the effectiveness of two kinds of search paradigms in the context of semantic hashing, BRCD first aligns the semantic spaces between the teacher and student models through a contrastive knowledge distillation objective. Additionally, to eliminate noisy augmentations and ensure robust optimization, a cluster-based method within the knowledge distillation process is introduced. Furthermore, through a bit-level analysis, we uncover the presence of redundancy bits resulting from the bit independence property. To mitigate these effects, we introduce a bit mask mechanism in our knowledge distillation objective. Finally, extensive experiments not only showcase the noteworthy performance of our BRCD method in comparison to other knowledge distillation methods but also substantiate the generality of our methods across diverse semantic hashing models and backbones. The code for BRCD is available at https://***/hly1998/BRCD. Copyright © 2024, 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

GGTS: FPGA-Based General Ground Test System for Space-Borne Equipment 6

GGTS: FPGA-Based General Ground Test System for Space-Borne ...

引用

6th IEEE International Conference on computer and Communication Systems, ICCCS 2021

作者： Mang, Jialu Qiu, Zhiliang Pan, Weitao Dong, Meng Wu, Min State Key Laboratory of the Integrated Services Networks Xidian University Xi'an China Beijing Institute of Computer Technology and Application Beijing China

ISBN: (纸本)9780738126043

Space-borne equipment has the characteristics of long in-orbit work cycle, high risk, high development cost, and high maintenance cost. Therefore, it needs to pass the satellite payload ground test before launching. As different space-borne equipment has different testing requirements, it is necessary to develop a variety of corresponding ground test equipment, which leads to problems such as high development costs, long cycles, and difficult software maintenance and updates. This paper designs a set of FPGA-based ground test system for space-borne equipment based on the demand characteristics of satellite equipment ground testing. The system integrates the external interfaces of different onboard equipment into a universal interface adapter, and combines the network tester to test the functions and performance of the onboard equipment. The system efficiently solves the problem of repeated development of ground testing equipment and improves the efficiency of ground testing of space-borne equipment. The application results show that the system has significantly improved the test efficiency in the ground test. © 2021 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases 23

Domain Adaptive Code Completion via Language Models and Deco...

引用

Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering

作者： Ze Tang Jidong Ge Shangqing Liu Tingwei Zhu Tongtong Xu Liguo Huang Bin Luo National Key Laboratory for Novel Software Technology Nanjing University China Nanyang Technological University Singapore Huawei Software Engineering Application Technology China Department of Computer Science Southern Methodist University USA

ISBN: (纸本)9798350329964

Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, due to the lack of domain-specific knowledge, they may not be optimal in completing code that requires intensive domain knowledge for example completing the library names. Although there are several works that have confirmed the effectiveness of fine-tuning techniques to adapt language models for code completion in specific domains. They are limited by the need for constant fine-tuning of the model when the project is in constant *** address this limitation, in this paper, we propose kNM-LM, a retrieval-augmented language model (R-LM), that integrates domain knowledge into language models without fine-tuning. Different from previous techniques, our approach is able to automatically adapt to different language models and domains. Specifically, it utilizes the in-domain code to build the retrieval-based database decoupled from LM, and then combines it with LM through Bayesian inference to complete the code. The extensive experiments on the completion of intra-project and intra-scenario have confirmed that kNM-LM brings about appreciable enhancements when compared to CodeGPT and UnixCoder. A deep analysis of our tool including the responding speed, storage usage, specific type code completion, and API invocation completion has confirmed that kNM-LM provides satisfactory performance, which renders it highly appropriate for domain adaptive code completion. Furthermore, our approach operates without the requirement for direct access to the language model's parameters. As a result, it can seamlessly integrate with black-box code completion models, making it easy to integrate our approach as a plugin to further enhance the performance of these models.

关键词： domain adaptive code completion

来源：评论

学校读者我要写书评

暂无评论

application of SNNS Model Based On Multi-Dimensional Attention In Drone Radio Frequency Signal Classification

Application of SNNS Model Based On Multi-Dimensional Attenti...

引用

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

作者： Zheng Si Chao Liu Jianyu Liu Yinhao Zhou Henan Institute of Advanced Technology Zhengzhou University Zhengzhou Zhongke Institute of Integrated Circuit and System Application School of Computer Science Shanghai Key Laboratory of Data Science Fudan University

Spiking Neural Networks (SNNs) are attracting attention due to their energy efficiency and importance in neuromorphic computing. Therefore, we propose an SNN-based method for classifying drone RF signals in complex electromagnetic environments. Specifically, we designed a new SNNs model called Spiking-EfficientNet based on EfficientNetV2 and improved its performance with a multidimensional attention mechanism. Experimental results demonstrate that Spiking-EfficientNet achieved classification accuracy of 99.13% and 96.02% on the ZK RF and DroneDetectV2 datasets. Importantly, Spiking-EfficientNet not only outperforms traditional Artificial Neural Networks (ANNs) in performance, but also exhibits significantly lower energy consumption. The energy consumption is only 20.1% of EfficientNetV2, 2.56% of VGG11, 10.71% of ResNet18, and 61.15% of MobileNetV2. This study demonstrates the significant potential of SNNs in drone RF signal classification and provides a low-power solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A technique of internal relative transmission delay measurement and positioning error correction for GNSS pseudo-satellite systems

A technique of internal relative transmission delay measurem...

引用

IEEE Information technology and Mechatronics Engineering Conference (ITOEC)

作者： Yuexian Liang Li Zhao Yao Cheng Chunhui Li School of Computer Science and Engineering Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic Technology Guilin China

Internal transmission delay is one of the inherent system parameters of pseudo-satellite transmitters, and it is also one of the factors affecting the positioning service accuracy of pseudo-satellite systems. Aiming at the influence of the internal delay inconsistency deviation caused by the inconsistent components characteristics of different pseudo-satellites, a method of relative delay mensuration and compensating inside the pseudo-satellite transmitter is proposed. According to the structural characteristics of pseudo-satellite transmitter and receiver, a transmission delay measurement model is established, the total transmission delay of the pseudo-satellite transceiver system is measured by high-precision instruments, and the relative internal transmission delay between other pseudo-satellites is obtained by difference method based on one of the pseudo-satellites. Starting from the carrier phase observation equation, the positioning correction model based on single-difference carrier phase is established, and the measured value is converted into the delay compensation factor in the positioning algorithm model for positioning solution. Through the comparative analysis of the experimental results of the positioning solution before and after correction, the method can improve the positioning accuracy effectively, and the feasibility of the method is verified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unified Uncertainty Estimation for Cognitive Diagnosis Models

arXiv

引用

arXiv 2024年

作者： Wang, Fei Liu, Qi Chen, Enhong Liu, Chuanren Huang, Zhenya Wu, Jinze Wang, Shijin School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China The University of Tennessee Business Analytics and Statistics Knoxville United States iFLYTEK Research State Key Laboratory of Cognitive Intelligence Hefei China State Key Laboratory of Cognitive Intelligence Hefei China

Cognitive diagnosis models have been widely used in different areas, especially intelligent education, to measure users’ proficiency levels on knowledge concepts, based on which users can get personalized instructions. As the measurement is not always reliable due to the weak links of the models and data, the uncertainty of measurement also offers important information for decisions. However, the research on the uncertainty estimation lags behind that on advanced model structures for cognitive diagnosis. Existing approaches have limited efficiency and leave an academic blank for sophisticated models which have interaction function parameters (e.g., deep learning-based models). To address these problems, we propose a unified uncertainty estimation approach for a wide range of cognitive diagnosis models. Specifically, based on the idea of estimating the posterior distributions of cognitive diagnosis model parameters, we first provide a unified objective function for mini-batch based optimization that can be more efficiently applied to a wide range of models and large datasets. Then, we modify the reparameterization approach in order to adapt to parameters defined on different domains. Furthermore, we decompose the uncertainty of diagnostic parameters into data aspect and model aspect, which better explains the source of uncertainty. Extensive experiments demonstrate that our method is effective and can provide useful insights into the uncertainty of cognitive diagnosis. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

A Fusion Neural Network Incorporating Attention for Sensor-Based Human Activity Recognition 3

A Fusion Neural Network Incorporating Attention for Sensor-B...

引用

3rd International Conference on computer Vision, Image and Deep Learning and International Conference on computer Engineering and applications, CVIDL and ICCEA 2022

作者： Lu, Limeng Zhang, Chuanlin Cao, Kai Deng, Dao Institute of Chinese Ethnic Information Technology Northwest Minzu University Lanzhou China Key Laboratory of China's Ethnic Languages and Information Technology Ministry of Education Lanzhou China Northwest Minzu University School of Mathematics and Computer Science Lanzhou China Northwest Minzu University Key Laboratory of Streaming Data Computing Technologies and Application Lanzhou China

ISBN: (纸本)9781665459112

Even though the RNN, LSTM, and other networks are used to extract dependencies in time series, sensor-based human behavior recognition (HAR) still faces some difficulties, and the ability of deep learning (DL) networks to extract features still needs to be improved. We propose a fusion neural network in which an optimized small optimized Convolutional Block Attention Module (MP-CBAM) is suitable for HAR tasks to extract samples. The MP-CBAM is added to two branches Convolutional Neural Network (CNN) with different convolution kernel sizes, and the fused features are labeled with GRU for temporal dependence. Then the softmax function is used for classification. We validate on benchmark datasets UCI-HAR and WISDM and accuracies of 97.15% and 9S.9S% are obtained, respectively, demonstrating the adaptation of our framework to both single-sensor and multi-sensor devices. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Gradient Sign Inversion: Making an Adversarial Attack a Good Defense

Gradient Sign Inversion: Making an Adversarial Attack a Good...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaojian Ji Li Dong Rangding Wang Diqun Yan Yang Yin Jinyu Tian Department of Computer Science Ningbo University Zhejiang Key Laboratory of Mobile Network Application Technology Geely Auto Central Research Institute School of Computer Science and Engineering Macau University of Science and Technology

Deep neural networks have been proven vulnerable to deliberately crafted adversarial example, which cause serious safety and security concerns. Many defense approaches were proposed to resist such threats. However, existing defenses such as pre-compression or adversarial training would degrade the model performance on clean images or incur heavy computational costs. In this work, we propose a plug-and-play defensive module Gradient Sign Inversion (GSI) to defend gradient-based attack. Essentially, GSI attempts to inverse the direction of the backpropagated gradient for the victim model, disturbing the adversarial example generation of the attacking while retaining the performance of the vanilla network on genuine inputs. Specifically, an additive model based on periodic trigonometric function is established by investigating the necessary conditions that a suitable defensive module should have. By enforcing constraints on the defensive module, the parameters of GSI are determined, accompanied by a theoretical justification. Interestingly, we observe that the proposed GSI not only prevents the gradient-based adversarial attack, but can even improve the confidence of the ground-truth label when initiating an attack, making the attack betray as a defense. Source code is publicly available at https://***/JidaDiao/GSI.

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：