检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hou, Xia Li, Qifeng Yang, Jian Li, Tongliang Chai, Linzheng Wu, Xianjie Ji, Hangyuan Li, Zhoujun Nie, Jixuan Dun, Jingbo Song, Wenfeng Computer School Beijing Information Science & Technology University China State Key Laboratory of Complex & Critical Software Environment Beihang University China

Instruction tuning as an effective technique aligns the outputs of large language models (LLMs) with human preference. But how to generate the seasonal multi-turn dialogues from raw documents for instruction tuning still requires further exploration. In this paper, we present a novel framework named R2S that leverages the CoD-Chain of Dialogue logic to guide large language models (LLMs) in generating knowledge-intensive multi-turn dialogues for instruction tuning. By integrating raw documents from both open-source datasets and domain-specific web-crawled documents into a benchmark K-BENCH, we cover diverse areas such as Wikipedia (English), science (Chinese), and Artifacts (Chinese). Our approach first decides the logic flow of the current dialogue and then prompts LLMs to produce key phrases for sourcing relevant response content. This methodology enables the creation of the GINSTRUCT instruction dataset, retaining raw document knowledge within dialogue-style interactions. Utilizing this dataset, we fine-tune GLLM, a model designed to transform raw documents into structured multi-turn dialogues, thereby injecting comprehensive domain knowledge into the SFT model for enhanced instruction tuning. This work signifies a stride towards refining the adaptability and effectiveness of LLMs in processing and generating more accurate, contextually nuanced responses across various *** Codes 68T50 © 2024, CC BY.

关键词： Web crawler

来源：评论

学校读者我要写书评

暂无评论

DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization

arXiv

引用

arXiv 2023年

作者： Guo, Jintao Qi, Lei Shi, Yinghuan State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China School of Computer Science and Engineering Southeast University Bangladesh

Deep Neural Networks have exhibited considerable success in various visual tasks. However, when applied to unseen test datasets, state-of-the-art models often suffer performance degradation due to domain shifts. In this paper, we introduce a novel approach for domain generalization from a novel perspective of enhancing the robustness of channels in feature maps to domain shifts. We observe that models trained on source domains contain a substantial number of channels that exhibit unstable activations across different domains, which are inclined to capture domain-specific features and behave abnormally when exposed to unseen target domains. To address the issue, we propose a DomainDrop framework to continuously enhance the channel robustness to domain shifts, where a domain discriminator is used to identify and drop unstable channels in feature maps of each network layer during forward propagation. We theoretically prove that our framework could effectively lower the generalization bound. Extensive experiments on several benchmarks indicate that our framework achieves state-of-the-art performance compared to other competing methods. Our code is available at https://***/lingeringlight/DomainDrop. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Safe Probabilistic Invariance Verification for Stochastic Discrete-Time Dynamical Systems

Safe Probabilistic Invariance Verification for Stochastic Di...

引用

IEEE Conference on Decision and Control

作者： Yiqing Yu Taoran Wu Bican Xia Ji Wang Bai Xue Department of Information Science School of Mathematical Sciences Peking University China State Key Laboratory of Computer Science Institute of Software CAS China State Key Laboratory of High Performance Computing and College of Computer Science and Technology National University of Defense Technology China

Ensuring safety through set invariance has proven a useful method in a variety of applications in robotics and control. In this paper, we focus on the safe probabilistic invariance verification problem for discrete-time dynamical systems subject to stochastic disturbances over the infinite time horizon. Our goal is to compute the lower and upper bounds of the liveness probability for a given safe set and set of initial states. This probability represents the likelihood that the system will remain within the safe set for all time. To address this problem, we draw inspiration from stochastic barrier certificates for safety verification and build upon the findings in [21], where an equation was presented for exact probability analysis. We present two sets of optimizations and demonstrate their effectiveness through two examples, using semi-definite programming tools.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Liu, Xu-Hui Liu, Tian-Shuo Jiang, Shengyi Chen, Ruifeng Zhang, Zhilong Chen, Xinwei Yu, Yang National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Polixir Technologies China Department of Computer Science The University of Hong Kong Hong Kong

Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, Energy-guided DIffusion Sampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions to distill this knowledge for enhanced data generation in the online phase. The theoretical analysis demonstrates that EDIS exhibits reduced suboptimality compared to solely utilizing online data or directly reusing offline data. EDIS is a plug-in approach and can be combined with existing methods in offline-to-online RL setting. By implementing EDIS to off-the-shelf methods Cal-QL and IQL, we observe a notable 20% average improvement in empirical performance on MuJoCo, AntMaze, and Adroit environments. Code is available at https://***/liuxhym/EDIS. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation

Constructing and Exploring Intermediate Domains in Mixed Dom...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Qinghe Ma Jian Zhang Lei Qi Qian Yu Yinghuan Shi Yang Gao State Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Nanjing University China Nanjing University Southeast University Shandong Women's University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Both limited annotation and domain shift are preva-lent challenges in medical image segmentation. Traditional semi-supervised segmentation and unsupervised do-main adaptation methods address one of these issues sepa-rately. However, the coexistence of limited annotation and domain shift is quite common, which motivates us to in-troduce a novel and challenging scenario: Mixed Domain Semi-supervised medical image Segmentation (MiDSS). In this scenario, we handle data from multiple medical cen-ters, with limited annotations available for a single do-main and a large amount of unlabeled data from multi-ple domains. We found that the key to solving the prob-lem lies in how to generate reliable pseudo labels for the unlabeled data in the presence of domain shift with la-beled data. To tackle this issue, we employ Unified Copy-Paste (UCP) between images to construct intermediate do-mains, facilitating the knowledge transfer from the do-main of labeled data to the domains of unlabeled data. To fully utilize the information within the intermediate do-main, we propose a symmetric Guidance training strategy (SymGD), which additionally offers direct guidance to un-labeled data by merging pseudo labels from intermediate samples. Subsequently, we introduce a Training Process aware Random Amplitude MixUp (TP-RAM) to progres-sively incorporate style-transition components into inter-mediate samples. Compared with existing state-of-the-art approaches, our method achieves a notable 13.57% im-provement in Dice score on Prostate dataset, as demon-strated on three public datasets. Our code is available at https://***/MQinghe/MiDSS

关键词： Training Image segmentation computer vision Codes Annotations Merging Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Joint DNN Partition and Thread Allocation Optimization for Energy-Harvesting MEC Systems

Joint DNN Partition and Thread Allocation Optimization for E...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Yizhou Shi Liying Li Yue Zeng Peijin Cong Junlong Zhou School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Mobile Communications Research Laboratory Southeast University Nanjing China Key Laboratory of Embedded System and Service Computing (Tongji University) Ministry of Education Shanghai China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Deep neural networks (DNNs) have demonstrated exceptional performance, leading to diverse applications across various mobile devices (MDs). Considering factors like portability and environmental sustainability, an increasing number of MDs are adopting energy harvesting (EH) techniques for power supply. However, the computational intensity of DNNs presents significant challenges for their deployment on these resource-constrained devices. Existing approaches often employ DNN partition or offloading to mitigate the time and energy consumption associated with running DNNs on MDs. Nonetheless, existing methods frequently fall short in accurately modeling the execution time of DNNs, and do not consider to use thread allocation for further latency and energy consumption optimization. To solve these problems, we propose a dynamic DNN partition and thread allocation method to optimize the latency and energy consumption of running DNNs on EH-enabled MDs. Specifically, we first investigate the relationship between DNN inference latency and allocated threads and establish an accurate DNN latency prediction model. Based on the prediction model, a DRL-based DNN partition (DDP) algorithm is designed to find the optimal partitions for DNNs. A thread allocation (TA) algorithm is proposed to reduce the inference latency. Experimental results from our test-bed platform demonstrate that compared to four benchmarking methods, our scheme can reduce DNN inference latency and energy consumption by up to 37.3% and 38.5%.

关键词： Energy consumption Instruction sets Heuristic algorithms Artificial neural networks Predictive models Prediction algorithms Inference algorithms Partitioning algorithms Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

A missing physical fitness test data classification method based on MLP

A missing physical fitness test data classification method b...

引用

IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)

作者： Peng Che Zhenlian Peng Buqing Cao Jianxun Liu Tieping Chen Runqing Fan School of Computer Science and Engineering Hunan Provincial Key Laboratory for Services Computing and Novel Software Technology Hunan University of Science and Technology Xiangtan China School of Physical Education Hunan University of Science and Technology Xiangtan China

In recent years, the physical health status of college students have been attached by the country and all universities. Much effort is spent every year to conduct physical health tests, generating a large amount of physical fitness data. Due to some irresistible reasons, such as entering incorrect data or students being unable to participate in some physical fitness programs, missing data exists in the physical fitness test, and the calculation of total points according to the existing rules of weighted summation may lead to inaccurate classification of some students grades. To this end, a classification method based on physical fitness test data with missing items is proposed in this paper. Firstly, the method collects the raw data set and constructs a structured data set. Then, the MLP method is used to construct a classifier model to classify the test data set with missing items. Finally, compared experiments are conducted with the training model constructed by GaussianNB, SVM and XGBoost and the results show that the classification effect of MLP is excellent, and the accuracy of classification can reach 93.29 %.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

引用

Engineering 2024年第2期33卷 178-189页

作者： Xiaoming Yuan Jiahui Chen Ning Zhang Qiang(John)Ye Changle Li Chunsheng Zhu Xuemin Sherman Shen Qinhuangdao Branch Campus Northeastern UniversityQinhuangdao 066004China State Key Laboratory of Integrated Services Networks&the Research Institute of Smart Transportation Xidian UniversityXi’an 710071China Department of Electrical and Computer Engineering University of WindsorWindsorON N9B 3P4Canada Department of Electrical and Software Engineering University of CalgaryCalgaryAB T2N 1N4Canada SUSTech Institute of Future Networks Southern University of Science and TechnologyShenzhen 518055China Department of Electrical and Computer Engineering University of WaterlooWaterlooON N2L 3G1Canada

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility *** order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client *** enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for *** problem is decoupled into two convex *** to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration *** on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their *** simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

关键词： Knowledge sharing Internet of Vehicles Federated learning Broad learning Reconfigurable intelligent surfaces Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Nimbus: Toward Speed Up Function Signature Recovery via Input Resizing and Multi-Task Learning

Nimbus: Toward Speed Up Function Signature Recovery via Inpu...

引用

IEEE International Conference on software Quality, Reliability and Security (QRS)

作者： Yi Qian Ligeng Chen Yuyang Wang Bing Mao Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

Function signature recovery is important for many binary analysis tasks such as control-flow integrity enforcement, clone detection, and bug finding. Existing works try to substitute learning-based methods with rule-based methods to reduce human *** made considerable efforts to enhance the system’s performance, which also bring the side effect of higher resource consumption. However, recovering the function signature is more about providing information for subsequent tasks, and both efficiency and performance are *** this paper, we first propose a method called Nimbus for efficient function signature recovery that furthest reduces the whole-process resource consumption without performance loss. Thanks to information bias and task relation (i.e., the relation between parameter count and parameter type recovery), we utilize selective inputs and introduce multi-task learning (MTL) structure for function signature recovery to reduce computational resource consumption, and fully leverage mutual information. Our experimental results show that, with only about the one-eighth processing time of the state-of-the-art method, we even achieve about 1% more prediction accuracy over all function signature recovery tasks.

关键词： Learning systems Neural networks computer bugs Cloning software quality Multitasking software reliability

来源：评论

学校读者我要写书评

暂无评论

SC-GAT: Web Services Classification Based on Graph Attention Network 16th

SC-GAT: Web Services Classification Based on Graph Attention...

引用

16th EAI International Conference on Collaborative Computing: Networking, Applications, and Worksharing, CollaborateCom 2020

作者： Peng, Mi Cao, Buqing Chen, Junjie Liu, Jianxun Li, Bing School of Computer Science and Engineering & Hunan Provincial Key Laboratory for Services Computing and Novel Software Technology Hunan University of Science and Technology Xiangtan China School of Computer Wuhan University Wuhan China

ISBN: (纸本)9783030675363

The classification of Web services with high similarity is conducive to the promotion for service management and service discovery. With the increasing number of Web services, how to accurately and efficiently classify the Web services becomes an urgent and challenging task. Although the existing methods achieve significant results in the task for service classification via integrating the structure information of service network with the content features of service node, it fails to discriminate the importance of neighbor services in the service network on the service node needed to be classified. To solve this problem, we propose a Web services classification method based on graph attention network. Firstly, according to the composition and shared annotation relationship of Web services, it applies the description documents, tags of Web services and the call relationship between mashups and services to build a service relationship network. Then, the attention coefficient of service nodes in the network is calculated by the self-attention mechanism, and different service nodes in the neighborhood are assigned different weights to classify Web services. Through the graph attention network, the content features of Web service can be well integrated with its structure information. Also, the learned attention weight is more interpretable. The experimental results on the real dataset of ProgrammableWeb platform show that the precision, recall and macro-F1 of the proposed method are greatly improved compared to those of GCN, Node2vec, DeepWalk and Line. © 2021, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Web services

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：