检索结果-南通市图书馆

同方期刊数据库

GPS: graph contrastive learning via multi-scale augmented views from adversarial pooling

在线全文

学校读者我要写书评

暂无评论

science China(Information sciences) 2025年第1期68卷 145-158页

作者： Wei JU Yiyang GU Zhengyang MAO Ziyue QIAO Yifang QIN Xiao LUO Hui XIONG Ming ZHANG School of computer science National Key Laboratory for Multimedia Information ProcessingPeking University Artificial Intelligence Thrust The Hong Kong University of Science and Technology Department of computer science University of California

Self-supervised graph representation learning has recently shown considerable promise in a range of fields, including bioinformatics and social networks. A large number of graph contrastive learning approaches have shown promising performance for representation learning on graphs, which train models by maximizing agreement between original graphs and their augmented views(i.e., positive views). Unfortunately, these methods usually involve pre-defined augmentation strategies based on the knowledge of human experts. Moreover, these strategies may fail to generate challenging positive views to provide sufficient supervision signals. In this paper, we present a novel approach named graph pooling contrast(GPS) to address these *** by the fact that graph pooling can adaptively coarsen the graph with the removal of redundancy, we rethink graph pooling and leverage it to automatically generate multi-scale positive views with varying emphasis on providing challenging positives and preserving semantics, i.e., strongly-augmented view and weakly-augmented view. Then, we incorporate both views into a joint contrastive learning framework with similarity learning and consistency learning, where our pooling module is adversarially trained with respect to the encoder for adversarial robustness. Experiments on twelve datasets on both graph classification and transfer learning tasks verify the superiority of the proposed method over its counterparts.

关键词： graph representation learning graph neural networks graph contrastive learning graph augmentations graph pooling

Deep learning-based software engineering: progress,challenges, and opportunities

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2025年第1期68卷 57-144页

作者： Xiangping CHEN Xing HU Yuan HUANG He JIANG Weixing JI Yanjie JIANG Yanyan JIANG Bo LIU Hui LIU Xiaochen LI Xiaoli LIAN Guozhu MENG Xin PENG Hailong SUN Lin SHI Bo WANG Chong WANG Jiayi WANG Tiantian WANG Jifeng XUAN Xin XIA Yibiao YANG Yixin YANG Li ZHANG Yuming ZHOU Lu ZHANG School of Journalism and Communication Sun Yat-sen University School of Software Technology Zhejiang University School of Software Engineering Sun Yat-sen University School of Software Dalian University of Technology School of computer science and Technology Beijing Institute of Technology key laboratory of High Confidence Software Technologies (Peking University) Ministry of EducationSchool of Computer Science Peking University state key laboratory for Novel Software Technology Nanjing University School of computer science and Engineering Beihang University Institute of Information Engineering Chinese Academy of Sciences School of computer science Fudan University state key laboratory of Complex & Critical Software Environment (CCSE) School of Software Beihang University School of computer and Information Technology Beijing Jiaotong University School of computer science and Technology Harbin Institute of Technology School of computer science Wuhan University Huawei Technologies

Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many studies have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However,although several surveys have provided overall pictures of the application of deep learning techniques in software engineering,they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this study, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically. For each of the selected subareas,we highlight the major advances achieved by applying deep learning techniques with pointers to the available datasets i

关键词： deep learning software engineering software benchmark software artifact representation survey

Edge-aware Feature Aggregation Network for Polyp Segmentation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2025年第1期22卷 101-116页

作者： Tao Zhou Yizhe Zhang Geng Chen Yi Zhou Ye Wu Deng-Ping Fan PCA lab Key Laboratory of Intelligent Perception and Systems for High-dimensional Information of Ministry of EducationSchool of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing210094China School of computer science and Engineering Northwestern Polytechnical University(NPU)Xi’an710129China School of computer science and Engineering Southeast UniversityNanjing211189China computer Vision lab ETH ZürichZürich8092Switzerland

Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer(CRC)in clinical ***,due to scale variation and blurry polyp boundaries,it is still a challenging task to achieve satisfactory segmentation performance with different scales and *** this study,we present a novel edge-aware feature aggregation network(EFA-Net)for polyp segmentation,which can fully make use of cross-level and multi-scale features to enhance the performance of polyp ***,we first present an edge-aware guidance module(EGM)to combine the low-level features with the high-level features to learn an edge-enhanced feature,which is incorporated into each decoder unit using a layer-by-layer ***,a scale-aware convolution module(SCM)is proposed to learn scale-aware features by using dilated convolutions with different ratios,in order to effectively deal with scale ***,a cross-level fusion module(CFM)is proposed to effectively integrate the cross-level features,which can exploit the local and global contextual ***,the outputs of CFMs are adaptively weighted by using the learned edge-aware feature,which are then used to produce multiple side-out segmentation *** results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and *** implementation code and segmentation maps will be publicly at https://***/taozh2017/EFANet.

关键词： Colorectal cancer polyp segmentation edge-aware guidance module scale-aware convolution module cross-level fusion module

Four-wave mixing Bragg scattering for small frequency shift from silicon coupled microrings

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics B 2025年第1期34卷 351-355页

作者： Chang Zhao Chao Wu Pingyu Zhu Yuxing Du Yan Wang Miaomiao Yu Kaikai Zhang Ping Xu Institute for Quantum Information&state key laboratory of High Performance Computing College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China

Frequency conversion is pivotal in nonlinear optics and quantum optics for manipulating and translating light signals across different wavelength *** frequency conversion between two light beams with a small frequency interval is a central *** this work,we design a pair of coupled silicon microrings wherein coupled-induced modesplitting exists to achieve a small frequency shift by the process of four-wave mixing Bragg *** an example,the signal can be up or down converted to the idler which is 15.5 GHz spaced when two pumps align with another pair of split *** results unveil the potential of coupled microring resonators for small interval frequency conversion in a high-fidelity,all-optical,and signal processing quantum frequency interface.

关键词： four-wave mixing Bragg scattering silicon coupled microrings

维普期刊数据库

COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection

在线全文

学校读者我要写书评

暂无评论

science China(Information sciences) 2025年第1期68卷 189-203页

作者： Xiaoqin ZHANG Zhenni YU Li ZHAO Deng-Ping FAN Guobao XIAO Zhejiang Province key laboratory of Intelligent Informatics for Safety and Emergency Wenzhou University Nankai International Advanced Research Institute (SHENZHEN FUTIAN) College of computer science Nankai University School of computer science and Technology Tongji University

We rethink the segment anything model(SAM) and propose a novel multiprompt network called COMPrompter for camouflaged object detection(COD). SAM has zero-shot generalization ability beyond other models and can provide an ideal framework for COD. Our network aims to enhance the single prompt strategy in SAM to a multiprompt strategy. To achieve this, we propose an edge gradient extraction module, which generates a mask containing gradient information regarding the boundaries of camouflaged objects. This gradient mask is then used as a novel boundary prompt, enhancing the segmentation process. Thereafter, we design a box-boundary mutual guidance module, which fosters more precise and comprehensive feature extraction via mutual guidance between a boundary prompt and a box prompt. This collaboration enhances the model's ability to accurately detect camouflaged objects. Moreover, we employ the discrete wavelet transform to extract high-frequency features from image embeddings. The high-frequency features serve as a supplementary component to the multiprompt ***, our COMPrompter guides the network to achieve enhanced segmentation results, thereby advancing the development of SAM in terms of COD. Experimental results across COD benchmarks demonstrate that COMPrompter achieves a cutting-edge performance, surpassing the current leading model by an average positive metric of 2.2% in COD10K. In the specific application of COD, the experimental results in polyp segmentation show that our model is superior to top-tier methods as well. The code will be made available at https://***/guobaoxiao/COMPrompter.

关键词： segment anything model camouflaged object detection boundary prompt

同方期刊数据库

B2-CuZr reinforced amorphous alloy matrix composites:A review

在线全文

学校读者我要写书评

暂无评论

China Foundry 2025年第1期22卷 1-11页

作者： Wei Guo Run-hua Huang Zhen Zhang Mi Zhao Jin-cheng Wang Yan-qiang Qiao Shu-lin Lü Shu-sen Wu state key lab of Materials Processing and Die&Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China state key laboratory of Solidification Processing Northwestern Polytechnical UniversityXi’an 710072China School of Aerospace Engineering Huazhong University of Science and TechnologyWuhan 430074China Research Institute of Huazhong University of science and Technology in Shenzhen Shenzhen 518057GuangdongChina

B2-CuZr phase reinforced amorphous alloy matrix composites has become one of the research hotspots in the field of materials science due to the“transformation-induced plasticity”phenomenon,which makes the composites show better macroscopic plastic deformability and obvious work-hardening behavior compared to the conventional amorphous alloy matrix composites reinforced with ductile ***,the in-situ metastable B2-CuZr phase tends to undergo eutectoid decomposition during solidification,and the volume fraction,size,and distribution of B2-CuZr phase are difficult to control,which limits the development and application of these *** date,much efforts have been made to solve the above problems through composition optimization,casting parameter tailoring,and post-processing *** this study,a review was given based on relevant studies,focusing on the predictive approach,reinforcing mechanism,and microstructure tailoring methods of B2-CuZr phase reinforced amorphous alloy matrix *** research focus and future prospects were also given for the future development of the present composite system.

关键词： amorphous alloy matrix composite B2-CuZr phase plasticity microstructure tailoring

维普期刊数据库

Experimental Study on Geometry Characteristics of Turbulent Premixed Flames for Natural Gas/Air Mixtures

在线全文

学校读者我要写书评

暂无评论

Journal of Thermal science 2025年第1期34卷 268-282页

作者： ZHENG Weilin WANG Qijiao XIAO Huahua CHEN Xiaoxiao XIE Fan ZENG Wen Liaoning key lab of Advanced Test Technology for Aerospace Propulsion System Shenyang Aerospace UniversityShenyang 110136China state key laboratory of Fire science University of science and Technology of ChinaHefei 230027China AVIC Shenyang Aircraft Design and Research Institute Shenyang 110035China

In this study,focusing on the geometry characteristics of spherical expanding flame,the turbulent premixed flames of natural gas/air mixtures were investigated in a fan-stirred turbulent *** effects of initial temperature(T=300-400 K),initial pressure(P=0.1-0.3 MPa),turbulence intensity(u'=1.0-2.7 m/s),oxygen volumetric percentage(φ(O_(2))=15%-21%)and carbon dioxide volumetric percentage(φ(CO_(2))=0-20%)were delved *** flame profile under the Cartesian coordinate system was derived from the schlieren images taken by the high-speed ***,from both macroscopic and microscopic perspectives,the influence of experimental conditions on the flame geometry characteristics was explored through flame front extraction,wavelet decomposition and network *** results demonstrate that for significant flame wrinkling,changes in species concentrations and turbulence intensity have more pronounced effects on the flame wrinkling *** wrinkling of the flame front maintains a certain degree of similarity,as evidenced by the locally concentrated distribution of the angles of the maximum fluctuation *** disturbance energy under large-scale(D6-D8)disturbances exhibits relatively high values with a similar trend,exerting a significant impact on the geometry characteristics of the flame *** peaks of correlation degree are scattered either with the decomposition scale or the development of flame radius,indicating no linear correlation between different detail ***,the probability distribution of node degrees in key wrinkled regions exhibits different trends with that of large-scale wrinkling and disturbance energy,especially with changes in initial *** occurs because the number of key wrinkles varies based on the perturbation's strength or the region's ***,an increase in the fluctuation frequency of the flame's local radius may not necessarily lead to an increase in the number of key folded regions.

关键词： geometry characteristics large-scale wrinkling wavelet decomposition network topology fan-stirred turbulent combustor

维普期刊数据库

RE-SEGNN:recurrent semantic evidence-aware graph neural network for temporal knowledge graph forecasting

在线全文

学校读者我要写书评

暂无评论

science China(Information sciences) 2025年第2期68卷 103-119页

作者： Wenyu CAI Mengfan LI Xuanhua SHI Yuanxin FAN Quntao ZHU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and Technology

Temporal knowledge graph(TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both entity and relation embedding to make predictions, ignoring the semantic correlations among different entities and relations within the same timestamp. This can lead to random and nonsensical predictions when unseen entities or relations occur. Furthermore, many existing models exhibit limitations in handling highly correlated historical facts with extensive temporal depth. They often either overlook such facts or overly accentuate the relationships between recurring past occurrences and their current counterparts. Due to the dynamic nature of TKG, effectively capturing the evolving semantics between different timestamps can be *** address these shortcomings, we propose the recurrent semantic evidenceaware graph neural network(RE-SEGNN), a novel graph neural network that can learn the semantics of entities and relations simultaneously. For the former challenge, our model can predict a possible answer to missing quadruples based on semantics when facing unseen entities or relations. For the latter problem, based on an obvious established force, both the recency and frequency of semantic history tend to confer a higher reference value for the current. We use the Hawkes process to compute the semantic trend, which allows the semantics of recent facts to gain more attention than those of distant facts. Experimental results show that RE-SEGNN outperforms all SOTA models in entity prediction on 6 widely used datasets, and 5 datasets in relation prediction. Furthermore, the case study shows how our model can deal with unseen entities and relations.

关键词： knowledge graph reasoning temporal knowledge graph Hawkes process semantic evidence

同方期刊数据库

Knowledge As Not Only Justified True Beliefs in Vision

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 297-299页

作者： Wenbo Zheng Fei-Yue Wang IEEE School of computer science and Artificial Intelligence Wuhan University of Technology Sanya science and Education Innovation Park of Wuhan University of Technology the state key laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences

COMPUTATIONAL knowledge vision [1] is emphasized as a novel perspective or field in this paper. It first proposes the visual hierarchy and its connection to knowledge, stating that knowledge is a justified true belief. To further the previous research, we concisely summarize our recent works and suggest a new direction that knowledge is also a thought framework in vision.

关键词： Computational modeling Visualization Artificial intelligence Data models Visual perception Visual databases Training data