检索结果-南通市图书馆

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

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

General Automatic Solution Generation for Social Problems

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2025年第1期22卷 145-159页

作者： Tong Niu Haoyu Huang Yu Du Weihao Zhang Luping Shi Rong Zhao center for Brain-Inspired computing Research(CBICR) Optical Memory National Engineering Research Centerand Department of Precision InstrumentTsinghua UniversityBeijing100084China IDG/McGovern Institute for Brain Research Tsinghua UniversityBeijing100084China THU-CET HIK Joint Research center for Brain-Inspired computing Beijing100084China

Given the escalating intricacy and multifaceted nature of contemporary social systems,manually generating solutions to address pertinent social issues has become a formidable *** response to this challenge,the rapid development of artificial intelligence has spurred the exploration of computational methodologies aimed at automatically generating ***,current methods for the auto-generation of solutions mainly concentrate on local social regulations that pertain to specific ***,we report an automatic social operating system(ASOS)designed for general social solution generation built upon agent-based models that enables both global and local analyses and regulations of social problems across spatial and temporal *** adopts a hypergraph with extensible social semantics for a comprehensive and structured representation of social *** also incorporates a generalized protocol for standardized hypergraph operations and a symbolic hybrid framework that delivers interpretable solutions,yielding a balance between regulatory efficacy and functional *** demonstrate the effectiveness of the ASOS,we apply it to the domain of averting extreme events within international oil futures *** generating a new trading role supplemented by new mechanisms,ASOS can adeptly discern precarious market conditions and make front-running interventions for nonprofit *** study demonstrated that ASOS provides an efficient and systematic approach for generating solutions for enhancing our society.

关键词： General automatic generation global-local regulation hypergraph social representation symbolic hybrid scheme generalized operation protocol

Attar: RRAM-based in-memory attention accelerator with software-hardware co-optimization

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

Science China(Information Sciences) 2025年第03期68卷 371-387页

作者： Bing LI Ying QI Ying WANG Yinhe HAN Information Engineering College Capital Normal University Research center for Intelligent computing Systems Institute of Computing TechnologyChinese Academy of Sciences

The attention mechanism has become a pivotal component in artificial intelligence, significantly enhancing the performance of deep learning applications. However, its quadratic computational complexity and intricate computations lead to substantial inefficiencies when processing long sequences. To address these challenges, we introduce Attar, a resistive random access memory(RRAM)-based in-memory accelerator designed to optimize attention mechanisms through software-hardware co-optimization. Attar leverages efficient Top-k pruning and quantization strategies to exploit the sparsity and redundancy of attention matrices, and incorporates an RRAM-based in-memory softmax engine by harnessing the versatility of the RRAM crossbar. Comprehensive evaluations demonstrate that Attar achieves a performance improvement of up to 4.88× and energy saving of 55.38% over previous computing-in-memory(CIM)-based accelerators across various models and datasets while maintaining comparable accuracy. This work underscores the potential of in-memory computing to enhance the efficiency of attention-based models without compromising their effectiveness.

关键词： RRAM computing-in-memory attention pruning quantization

同方期刊数据库

Decision making module based on stochastic magnetic tunnel junctions

在线全文

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2025年第1期68卷 198-205页

作者： Yifan Miao Li Zhao Yajun Zhang Zhe Yuan center for Advanced Quantum Studies and Department of Physics Beijing Normal UniversityBeijing 100875China Institute for Nanoelectric Devices and Quantum computing Fudan UniversityShanghai 200433China Interdisciplinary center for Theoretical Physics and Information Sciences Fudan UniversityShanghai 200433China

In biological neural systems,noise is ubiquitous but does not affect the correct decisions made in the complex cognitive ***-making in biological neural system is typically achieved by accumulating input information over a period of *** by recent developments in neurosciences,we design a decision-making module based on spintronic devices,utilizing superparamagnetic tunnel junctions as artificial *** feasibility of this decision-making module is verified through circuit *** a multi-layer perceptron as an example,the module significantly improves the accuracy of the perceptron in the handwritten digit recognition ***,the spintronic decision-making module offers advantages over the conventional pooling methods,such as adaptive decision time,high performance and the absence of analog-to-digital *** decision-making module is flexible to be integrated into artificial neural networks and provides a general yet effective solution to enhance performance against device noise.

关键词： neuromorphic computing spintronics magnetic tunnel junction neural networks

维普期刊数据库

Improving Multi-task GNNs for Molecular Property Prediction via Missing Label Imputation

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2025年第1期22卷 131-144页

作者： Fenyu Hu Dingshuo Chen Qiang Liu Shu Wu University of Chinese Academy of Sciences Beijing100190China center for Research on Intelligent Perception and computing State Key Laboratory of Multimodal Artificial Intelligence SystemsInstitute of AutomationChinese Academy of SciencesBeijing100190China

The prediction of molecular properties is a fundamental task in the field of drug ***,graph neural networks(GNNs)have been gaining prominence in this *** a molecule tends to have multiple correlated properties,there is a great need to develop the multi-task learning ability of ***,limited by expensive and time-consuming human annotations,collecting complete labels for each task is *** a result,most existing benchmarks involve many missing labels in training data,and the performance of GNNs is impaired due to the lack of sufficient supervision *** overcome this obstacle,we propose to improve multi-task molecular property prediction by missing label ***,a bipartite graph is first introduced to model the molecule-task co-occurrence ***,the imputation of missing labels is transformed into predicting missing edges on this bipartite *** predict the missing edges,a graph neural network is devised,which can learn the complex molecule-task co-occurrence *** that,we select reliable pseudo labels according to the uncertainty of the prediction *** with enough and reliable supervision information,our approach achieves state-of-the-art performance on a variety of real-world datasets.

关键词： Graph classification imbalance learning prediction bias mixture of experts multiview representations

Modification of Maxwell model for conductivity prediction of carbon nanotubes-filled polymer composites with tunneling effect

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

Applied Mathematics and Mechanics(English Edition) 2025年第1期46卷 25-36页

作者： Jue ZHU Longyuan LI Ningtao ZHU Zhejiang Provincial Engineering Research center for the Safety of Pressure Vessel and Pipeline Key Laboratory of Impact and Safety Engineering (Ningbo University) Ministry of Education School of Engineering Computing and Mathematics University of Plymouth Xi'an Zhanshi Testing & Engineering Co.Ltd.

Carbon nanotubes(CNTs) have garnered great attention in recent years due to their outstanding electrical, thermal, and mechanical properties. The incorporation of small amounts of CNTs in polymers can substantially improve the sensitivity of the polymer's electrical conductivity. This paper presents a modified Maxwell model to evaluate the electrical conductivity of CNTs-filled polymer composites by introducing a transition zone to account for the tunneling effect. In this modified Maxwell model, the CNTs-filled polymer composite is modeled as a three-phase composite, consisting of a matrix(polymer), inclusions(CNTs), and a transition zone(tunneling zone). The effective electrical conductivity(EEC) of the composite is calculated based on the volume fractions and electrical conductivities of the matrix, inclusions, and transition zone. The model's validity is confirmed through the use of available test data, which demonstrates its capability to accurately capture the nonlinear conductivity behavior observed in CNTs-polymer composites. This study offers valuable insights into the design of high-performance conductive polymer nanocomposites, and enhances the understanding of electrical conduction mechanisms in CNT-dispersed polymer composites.

关键词： carbon nanotube (CNT) composite electrical conductivity Maxwell model O242.2 O441.1 polymer tunneling

Boosting cationic and anionic redox activity of Li-rich layered oxide cathodes via Li/Ni disordered regulation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2025年第1期100卷 533-543页

作者： Zewen Liu Zhen Wu Hao Wang Xudong Zhang Yuanzhen Chen Yongning Liu Shengwu Guo Shenghua Chen Yanli Nan Yan Liu State Key Laboratory for Mechanical Behavior of Materials Xi’an Jiaotong UniversityXi’an 710049ShaanxiChina School of Materials Science and Engineering Xi’an University of Architecture and TechnologyXi’an 710055ShaanxiChina Hefei Advanced computing center Operation Management Corp Ltd Hefei 230088AnhuiChina Network Information center Xi’an Jiaotong UniversityXi’an 710049ShaanxiChina

Lithium-rich layered oxides (LLOs) are increasingly recognized as promising cathode materials for nextgeneration high-energy-density lithium-ion batteries (LIBs).However,they suffer from voltage decay and low initial Coulombic efficiency (ICE) due to severe structural degradation caused by irreversible O ***,we introduce a three-in-one strategy of increasing Ni and Mn content,along with Li/Ni disordering and TM–O covalency regulation to boost cationic and anionic redox activity simultaneously and thus enhance the electrochemical activity of *** target material,Li_(1.2)Ni_(0.168)Mn_(0.558)Co_(0.074)O_(2)(L1),exhibits an improved ICE of 87.2%and specific capacity of 293.2 mA h g^(-1)and minimal voltage decay of less than 0.53 m V cycle-1over 300 cycles at 1C,compared to Li_(1.2)Ni_(0.13)Mn_(0.54)Co_(0.13)O_(2)(Ls)(274.4 mA h g^(-1)for initial capacity,73.8%for ICE and voltage decay of 0.84 mV/cycle over 300 cycles at 1C).Theoretical calculations reveal that the density of states (DOS) area near the Fermi energy level for L1 is larger than that of Ls,indicating higher anionic and cationic redox reactivity than ***,L1 exhibits increased O-vacancy formation energy due to higher Li/Ni disordering of 4.76%(quantified by X-ray diffraction Rietveld refinement) and enhanced TM–O covalency,making lattice O release more difficult and thus improving electrochemical *** increased Li/Ni disordering also leads to more Ni^(2+)presence in the Li layer,which acts as a pillar during Li+de-embedding,improving structural *** research not only presents a viable approach to designing low-Co LLOs with enhanced capacity and ICE but also contributes significantly to the fundamental understanding of structural regulation in high-performance LIB cathodes.

关键词： Low-Co Li-rich layered oxides Li/Ni disordering TM-O covalency Cationic and anionic redox activity

维普期刊数据库

LiDAR-Visual SLAM with Integrated Semantic and Texture Information for Enhanced Ecological Monitoring Vehicle Localization

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 1401-1416页

作者： Yiqing Lu Liutao Zhao Qiankun Zhao Foreign Environmental Cooperation center Ministry of Ecology and Environment of PRCBeijing100035China Beijing computing center Co. Ltd.Beijing Academy of Science and TechnologyBeijing100083China Beijing Guyu Interactive Artificial Intelligence Application Co. Ltd.Beijing100024China

Ecological monitoring vehicles are equipped with a range of sensors and monitoring devices designed to gather data on ecological and environmental *** vehicles are crucial in various fields,including environmental science research,ecological and environmental monitoring projects,disaster response,and emergency management.A key method employed in these vehicles for achieving high-precision positioning is LiDAR(lightlaser detection and ranging)-Visual Simultaneous Localization and Mapping(SLAM).However,maintaining highprecision localization in complex scenarios,such as degraded environments or when dynamic objects are present,remains a significant *** address this issue,we integrate both semantic and texture information from LiDAR and cameras to enhance the robustness and efficiency of data ***,semantic information simplifies the modeling of scene elements,reducing the reliance on dense point clouds,which can be less ***,visual texture information complements LiDAR-Visual localization by providing additional contextual *** incorporating semantic and texture details frompaired images and point clouds,we significantly improve the quality of data association,thereby increasing the success rate of *** approach not only enhances the operational capabilities of ecological monitoring vehicles in complex environments but also contributes to improving the overall efficiency and effectiveness of ecological monitoring and environmental protection efforts.

关键词： LiDAR-Visual simultaneous localization and mapping integrated semantic texture information

Detection using mask adaptive transformers in unmanned aerial vehicle imagery

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

Optoelectronics Letters 2025年第2期21卷 113-120页

作者： YE Huibiao FAN Weiming GUO Yuping WANG Xuna ZHOU Dalin China Telecommunication Corporation Zhejiang Branch Hangzhou 310020China Innovation center for Smart Medical Technologies&Devices Binjiang Institute of Zhejiang UniversityHangzhou 100059China School of computing University of PortsmouthPortsmouthPO13HEUK

Drone photography is an essential building block of intelligent transportation,enabling wide-ranging monitoring,precise positioning,and rapid ***,the high computational cost of transformer-based methods in object detection tasks hinders real-time result transmission in drone target detection ***,we propose mask adaptive transformer (MAT) tailored for such ***,we introduce a structure that supports collaborative token sparsification in support windows,enhancing fault tolerance and reducing computational *** structure comprises two modules:a binary mask strategy and adaptive window self-attention (A-WSA).The binary mask strategy focuses on significant objects in various complex *** A-WSA mechanism is employed to self-attend for balance perfomance and computational cost to select objects and isolate all contextual *** experiments on the challenging CarPK and VisDrone datasets demonstrate the effectiveness and superiority of the proposed ***,it achieves a mean average precision (mAP@0.5) improvement of 1.25%over car detector based on you only look once version 5 (CD-YOLOv5) on the CarPK dataset and a 3.75%average precision(AP@0.5) improvement over cascaded zoom-in detector (CZ Det) on the VisDrone dataset.

关键词： token mask imagery

维普期刊数据库