检索结果-内蒙古大学图书馆

Argumentation Based Ontology Alignment Extraction 6th

学校读者我要写书评

暂无评论

Argumentation Based Ontology Alignment Extraction

6th International Conference on Advanced Machine Learning Technologies and Applications, AMLTA 2021

作者： Wu, Xiaojing Xue, Xingsi Hu, Wenyu Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology 33 Xuefu South Road Fuzhou Fujian350118 China Intelligent Information Processing Research Center Fujian University of Technology Fuzhou Fujian350118 China Institute of Artificial Intelligence Fujian University of Technology Fuzhou Fujian350118 China Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology Fuzhou Fujian350118 China School of Information Science and Engineering Fujian University of Technology Fuzhou Fujian350118 China

ISBN: (纸本)9783030697167

The ontology matching technique aims at establishing the correspondence between two ontologies’ entities to solve their heterogeneity problem. In the matching process, the quality of the single matcher’s alignment can not be ensured. Usually, multiple matches are required to work together to increase the evidence of potential matches or mismatches. Selecting, combining, and adjusting these ontology matches to obtain high-quality ontology comparisons is one of the main challenges in ontology matching. This paper proposes an Argumentation Framework (A.F.) based on the ontology extracting technique to address this challenge. First, the proposed approach obtains the alignments obtained by different ontology matches. It extracts the final alignment by debating the disputed entity correspondences with A.F. The experiment is conducted on the Bibliographic track provided by Ontology Alignment Evaluation Initiative (OAEI), and the statistical comparison with the state-of-the-art ontology matching techniques shows the effectiveness of the proposed approach. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Extraction

FlowX: Towards Explainable Graph Neural Networks via Message Flows

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gui, Shurui Yuan, Hao Wang, Jie Lao, Qicheng Li, Kang Ji, Shuiwang The Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States The Department of Electronic Engineering and Information Science University of Science and Technology of China Anhui Hefei230026 China The School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The West China Biomedical Big Data Center West China Hospital Sichuan Chengdu610041 China

We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. While most current methods focus on explaining graph nodes, edges, or features, we argue that, as the inherent functional mechanism of GNNs, message flows are more natural for performing explainability. To this end, we propose a novel method here, known as FlowX, to explain GNNs by identifying important message flows. To quantify the importance of flows, we propose to follow the philosophy of Shapley values from cooperative game theory. To tackle the complexity of computing all coalitions’ marginal contributions, we propose a flow sampling scheme to compute Shapley value approximations as initial assessments of further training. We then propose an information-controlled learning algorithm to train flow scores toward diverse explanation targets: necessary or sufficient explanations. Experimental studies on both synthetic and real-world datasets demonstrate that our proposed FlowX and its variants lead to improved explainability of GNNs. Copyright © 2022, The Authors. All rights reserved.

关键词： Message passing

A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liang, Siyuan Li, Longkang Fan, Yanbo Jia, Xiaojun Li, Jingzhi Wu, Baoyuan Cao, Xiaochun State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Data Science Secure Computing Lab of Big Data The Chinese University of Hong Kong Shenzhen China Tencent AI Lab Shenzhen China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Shenzhen China

Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model information. Most existing attack methods aim to minimize the true positive rate, which often shows poor attack performance, as another sub-optimal bounding box may be detected around the attacked bounding box to be the new true positive one. To settle this challenge, we propose to minimize the true positive rate and maximize the false positive rate, which can encourage more false positive objects to block the generation of new true positive bounding boxes. It is modeled as a multi-objective optimization (MOP) problem, of which the generic algorithm can search the Pareto-optimal. However, our task has more than two million decision variables, leading to low searching efficiency. Thus, we extend the standard Genetic Algorithm with Random Subset selection and Divide-and-Conquer, called GARSDC, which significantly improves the efficiency. Moreover, to alleviate the sensitivity to population quality in generic algorithms, we generate a gradient-prior initial population, utilizing the transferability between different detectors with similar backbones. Compared with the state-of-art attack methods, GARSDC decreases by an average 12.0 in the mAP and queries by about 1000 times in extensive experiments. Our codes can be found at https://***/LiangSiyuan21/ GARSDC. © 2022, CC BY.

关键词： Object detection

Divide and contrast: source-free domain adaptation via adaptive contrastive learning 22

学校读者我要写书评

暂无评论

Divide and contrast: source-free domain adaptation via adapt...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Ziyi Zhang Weikai Chen Hui Cheng Zhen Li Siyuan Li Liang Lin Guanbin Li National Key Laboratory of Novel Software Technology Nanjing University Nanjing China Tencent America School of Computer Science and Engineering Sun Yat-sen University Guangzhou China The Chinese University of Hong Kong Shenzhen China and Shenzhen Research Institute of Big Data Shenzhen China AI Lab School of Engineering Westlake University Hangzhou China

ISBN: (纸本)9781713871088

We investigate a practical domain adaptation task, called source-free unsupervised domain adaptation (SFUDA), where the source pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage self-supervised pseudo-labeling to achieve class-wise global alignment [1] or rely on local structure extraction that encourages the feature consistency among neighborhoods [2]. While impressive progress has been made, both lines of methods have their own drawbacks - the "global" approach is sensitive to noisy labels while the "local" counterpart suffers from the source bias. In this paper, we present Divide and Contrast (DaC), a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations. Based on the prediction confidence of the source model, DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals under an adaptive contrastive learning framework. Specifically, the source-like samples are utilized for learning global class clustering thanks to their relatively clean labels. The more noisy target-specific data are harnessed at the instance level for learning the intrinsic local structures. We further align the sourcelike domain with the target-specific samples using a memory-based maximum mean discrepancy (MMD) loss to reduce the distribution mismatch. Extensive experiments on VisDA, Office-Home, and the more challenging DomainNet have verified the superior performance of DaC over current state-of-the-art approaches.

关键词：

ScalabFS: A scalable BFS accelerator on HBM-enhanced FPGAs

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Kexin Liu, Chenhao Shao, Zhiyuan Wang, Zeke Wu, Minkang Chen, Jiajie Liao, Xiaofei Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan30074 China Collaborative Innovation Center of Artificial Intelligence Zhejiang University China

High Bandwidth Memory (HBM) provides massive aggregated memory bandwidth by exposing multiple memory channels to the processing units. To achieve high performance, an accelerator built on top of an FPGA configured with HBM (i.e., FPGA-HBM platform) needs to scale its performance according to the available memory channels. In this paper, we propose an accelerator for BFS (Breadth-First Search) algorithm, named as ScalabFS, that builds multiple processing elements to sufficiently exploit the high bandwidth of HBM to improve efficiency. We implement the prototype system of ScalabFS and conduct BFS in both real-world and synthetic scale-free graphs on Xilinx Alveo U280 FPGA card real hardware. The experimental results show that ScalabFS scales its performance almost linearly according to the available memory pseudo channels (PCs) from the HBM2 subsystem of U280. By fully using the 32 PCs and building 64 processing elements (PEs) on U280, ScalabFS achieves a performance up to 19.7 GTEPS (Giga Traversed Edges Per Second). When conducting BFS in sparse real-world graphs, ScalabFS achieves equivalent GTEPS to Gunrock running on the state-of-art Nvidia V100 GPU that features 64-PC HBM2 (twice memory bandwidth than U280). Copyright © 2021, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

Breaking the curse of space explosion: Towards effcient NAS with curriculum search 37

学校读者我要写书评

暂无评论

Breaking the curse of space explosion: Towards effcient NAS ...

37th International Conference on Machine Learning, ICML 2020

作者： Guo, Yong Chen, Yaofo Zheng, Yin Zhao, Peilin Chen, Jian Huang, Junzhou Tan, Mingkui School of Software Engineering South China University of Technology China Pazhou Laboratory China Weixin Group Tencent China Tencent AI Lab Tencent China Guangdong Key Laboratory of Big Data Analysis and Processing China

ISBN: (纸本)9781713821120

Neural architecture search (NAS) has become an important approach to automatically fnd effective architectures. To cover all possible good architectures, we need to search in an extremely large search space with billions of candidate architectures. More critically, given a large search space, we may face a very challenging issue of space explosion. However, due to the limitation of computational resources, we can only sample a very small proportion of the architectures, which provides insuffcient information for the training. As a result, existing methods may often produce suboptimal architectures. To alleviate this issue, we propose a curriculum search method that starts from a small search space and gradually incorporates the learned knowledge to guide the search in a large space. With the proposed search strategy, our Curriculum Neural Architecture Search (CNAS) method signifcantly improves the search effciency and fnds better architectures than existing NAS methods. Extensive experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of the proposed method. Copyright 2020 by the author(s).

关键词： Curricula

Image super-resolution via dynamic network

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tian, Chunwei Zhang, Xuanyu Zhang, Qi Yang, Mingming Ju, Zhaojie School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China Research & Development Institute Northwestern Polytechnical University Shenzhen China School of Economics and Management Harbin Institute of Technology at Weihai Weihai264209 China Tencent AI lab Shenzhen China School of Computing University of Portsmouth PortsmouthPO1 3HE United Kingdom

Convolutional neural networks depend on deep network architectures to extract accurate information for image super-resolution. However, obtained information of these convolutional neural networks cannot completely express predicted high-quality images for complex scenes. In this paper, we present a dynamic network for image super-resolution (DSRNet), which contains a residual enhancement block, wide enhancement block, feature refinement block and construction block. The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super-resolution. To enhance robustness of obtained super-resolution model for complex scenes, a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super-resolution model for varying scenes. To prevent interference of components in a wide enhancement block, a refinement block utilizes a stacked architecture to accurately learn obtained features. Also, a residual learning operation is embedded in the refinement block to prevent long-term dependency problem. Finally, a construction block is responsible for reconstructing high-quality images. Designed heterogeneous architecture can not only facilitate richer structural information, but also be lightweight, which is suitable for mobile digital devices. Experimental results show that our method is more competitive in terms of performance, recovering time of image super-resolution and complexity. The code of DSRNet can be obtained at https://***/hellloxiaotian/DSRNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

Towards making deep learning-based vulnerability detectors robust

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Zhen Tang, Jing Zou, Deqing Chen, Qian Xu, Shouhuai Zhang, Chao Li, Yichen Jin, Hai The National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Big Data Security Engineering Research Center School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China The University of Texas at San Antonio San AntonioTX78249 United States The University of Colorado Colorado Springs Colorado SpringsCO80918 United States Tsinghua University Beijing100084 China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention. In particular, deep learning-based vulnerability detectors, or DL-based detectors, are attractive because they do not need human experts to define features or patterns of vulnerabilities. However, such detectors' robustness is unclear. In this paper, we initiate the study in this aspect by demonstrating that DL-based detectors are not robust against simple code transformations, dubbed attacks in this paper, as these transformations may be leveraged for malicious purposes. As a first step towards making DL-based detectors robust against such attacks, we propose an innovative framework, dubbed ZigZag, which is centered at (i) decoupling feature learning and classifier learning and (ii) using a ZigZag-style strategy to iteratively refine them until they converge to robust features and robust classifiers. Experimental results show that the ZigZag framework can substantially improve the robustness of DL-based detectors. Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

Hexagonally ordered microbowl arrays decorated with ultrathin CuInS_(2) nanosheets for enhanced photoelectrochemical performance

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2020年第12期29卷 134-142页

作者： Ming Li Le Chen Yanjie Su Huan Yin Kexiang Hu State Key Laboratory of Transducer Technology Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghai 200050China School of Electronic Engineering and Automation Guilin University of Electronic TechnologyKey Laboratory of Optoelectronic Information Processing of Guangxi Colleges and Uniy/ersitiesGuilin 541004GuangxiChina Key Laboratory for Thin Film and Microfabrication of the Ministry of Education Department of Micro/Nano ElectronicsSchool of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China National and Local Joint Engineering Laboratory of Internet Technology on Mine School of Information and Control EngineeringChina University of Mining and TechnologyXuzhou 221008JiangsuChina School of Physics and Telecommunication Engineering Guangxi Colleges and Universities Key Lab of Complex System Optimization and Big Data ProcessingYulin Normal UniversityYulin 537400GuangxiChina

This paper demonstrates the design and fabrication of three-dimensional(3 D) hexagonally ordered microbowl arrays(MBAs) decorated with Cu In S2 nanosheets for enhanced photoelectrochemical(PEC) performance. The 3 D MBAs are fabricated by a micro-fabrication technique. The ultrathin CuInS2 nanosheets are grown on the 3 D electrodes by solvothermal transformation of Cu film. The photocurrent density of 3 D photocathode(CuInS2@MBAs) is about two times higher than that of the planar counterpart(CuInS2@Planar). The improved PEC performance can be ascribed to the elevated light trapping ability and the increased surface area for loading photocatalysts. In addition, CdS quantum dots as cocatalysts are modified onto the Cu In S2 nanosheets to further enhance the PEC activity because the formed p-n heterojunction can accelerate the separation of photogenerated carriers. As a result, the 3 D photocathode of CuInS2/CdS@MBAs shows an optimal incident photon to current efficiency of 10% at the wavelength of400 nm. It is believed that this work can be generalized to design other hierarchical 3 D photoelectrodes for improved solar water splitting.

关键词： Microbowl array CuInS_(2) Nanosheet Photocathode Photoelectrochemical performance