检索结果-南通市图书馆

Physical information-enhanced graph neural network for predicting phase separation

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 2024年第7期33卷 278-283页

作者：张亚强王煦文王雅楠郑文 Institute of Public-Safety and Big Data College of Computer Science and Technology(College of Data Science)Taiyuan University of TechnologyJinzhong 030600China Shanxi Engineering Research Centre for Intelligent Data Assisted Treatment Changzhi Medical CollegeChangzhi 046000China Innovation Academy for Microsatellites of Chinese Academy of Sciences Shanghai 200050China

Although phase separation is a ubiquitous phenomenon, the interactions between multiple components make it difficult to accurately model and predict. In recent years, machine learning has been widely used in physics simulations. Here,we present a physical information-enhanced graph neural network(PIENet) to simulate and predict the evolution of phase separation. The accuracy of our model in predicting particle positions is improved by 40.3% and 51.77% compared with CNN and SVM respectively. Moreover, we design an order parameter based on local density to measure the evolution of phase separation and analyze the systematic changes with different repulsion coefficients and different Schmidt *** results demonstrate that our model can achieve long-term accurate predictions of order parameters without requiring complex handcrafted features. These results prove that graph neural networks can become new tools and methods for predicting the structure and properties of complex physical systems.

关键词： graph neural network phase separation machine learning dissipative particle dynamics

Combining graph neural network with deep reinforcement learning for resource allocation in computing force networks

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2024年第5期25卷 701-712页

作者： Xueying HAN Mingxi XIE Ke YU Xiaohong HUANG Zongpeng DU Huijuan YAO School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China School of Artificial Intelligence Beijing University of Posts and TelecommunicationsBeijing 100876China Department of Infrastructure network Technology Research China Mobile Research InstituteBeijing 100032China

Fueled by the explosive growth of ultra-low-latency and real-time applications with specific computing and network performance requirements,the computing force network(CFN)has become a hot research *** primary CFN challenge is to leverage network resources and computing *** recent advances in deep reinforcement learning(DRL)have brought significant improvement in network optimization,these methods still suffer from topology changes and fail to generalize for those topologies not seen in *** paper proposes a graph neural network(GNN)based DRL framework to accommodate network trafic and computing resources jointly and *** taking advantage of the generalization capability in GNN,the proposed method can operate over variable topologies and obtain higher performance than the other DRL methods.

关键词： Computing force network Routing optimization Deep learning graph neural network Resource allocation

Dynamic interwell connectivity analysis of multi-layer waterflooding reservoirs based on an improved graph neural network

在线全文

学校读者我要写书评

暂无评论

Petroleum Science 2024年第2期21卷 1062-1080页

作者： Zhao-Qin Huang Zhao-Xu Wang Hui-Fang Hu Shi-Ming Zhang Yong-Xing Liang Qi Guo Jun Yao School of Petroleum Engineering China University of Petroleum(East China)Qingdao266580ShandongChina Exploration and Development Research Institute Shengli OilfieldSINOPECDongying257015ShandongChina

The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oilfields generally have the characteristics of thin and many layers, so multi-layer joint production is usually adopted. It remains a challenge to ensure the accuracy of splitting and dynamic connectivity in each layer of the injection-production wells with limited field data. The three-dimensional well pattern of multi-layer reservoir and the relationship between injection-production wells can be equivalent to a directional heterogeneous graph. In this paper, an improved graph neural network is proposed to construct an interacting process mimics the real interwell flow regularity. In detail, this method is used to split injection and production rates by combining permeability, porosity and effective thickness, and to invert the dynamic connectivity in each layer of the injection-production wells by attention *** on the material balance and physical information, the overall connectivity from the injection wells,through the water injection layers to the production layers and the output of final production wells is established. Meanwhile, the change of well pattern caused by perforation, plugging and switching of wells at different times is achieved by updated graph structure in spatial and temporal ways. The effectiveness of the method is verified by a combination of reservoir numerical simulation examples and field example. The method corresponds to the actual situation of the reservoir, has wide adaptability and low cost, has good practical value, and provides a reference for adjusting the injection-production relationship of the reservoir and the development of the remaining oil.

关键词： graph neural network Dynamic interwell connectivity Production-injection splitting Attention mechanism Multi-layer reservoir

Heterophilic graph neural network Based on Spatial and Frequency Domain Adaptive Embedding Mechanism

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第5期139卷 1701-1731页

作者： Lanze Zhang Yijun Gu Jingjie Peng College of Information and Cyber Security People’s Public Security University of ChinaBeijing100038China

graph neural networks(GNNs)play a significant role in tasks related to homophilic *** GNNs,based on the assumption of homophily,employ low-pass filters for neighboring nodes to achieve information aggregation and ***,in heterophilic graphs,nodes from different categories often establish connections,while nodes of the same category are located further apart in the graph *** characteristic poses challenges to traditional GNNs,leading to issues of“distant node modeling deficiency”and“failure of the homophily assumption”.In response,this paper introduces the Spatial-Frequency domain Adaptive Heterophilic graph neural networks(SFA-HGNN),which integrates adaptive embedding mechanisms for both spatial and frequency domains to address the aforementioned ***,for the first problem,we propose the“Distant Spatial Embedding Module”,aiming to select and aggregate distant nodes through high-order randomwalk transition probabilities to enhance modeling *** the second issue,we design the“Proximal Frequency Domain Embedding Module”,constructing adaptive filters to separate high and low-frequency signals of nodes,and introduce frequency-domain guided attention mechanisms to fuse the relevant information,thereby reducing the noise introduced by the failure of the homophily *** deploy the SFA-HGNN on six publicly available heterophilic networks,achieving state-of-the-art results in four of ***,we elaborate on the hyperparameter selection mechanism and validate the performance of each module through experimentation,demonstrating a positive correlation between“node structural similarity”,“node attribute vector similarity”,and“node homophily”in heterophilic networks.

关键词： Heterophilic graph graph neural network graph representation learning failure of the homophily assumption

Transfer learning enhanced graph neural network for aldehyde oxidase metabolism prediction and its experimental application

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

Acta Pharmaceutica Sinica B 2024年第2期14卷 623-634页

作者： Jiacheng Xiong Rongrong Cui Zhaojun Li Wei Zhang Runze Zhang Zunyun Fu Xiaohong Liu Zhenghao Li Kaixian Chen Mingyue Zheng Drug Discovery and Design Center State Key Laboratory of Drug ResearchShanghai Institute of Materia MedicaChinese Academy of SciencesShanghai 201203China University of Chinese Academy of Sciences Beijing 100049China College of Computer and Information Engineering Dezhou UniversityDezhou 253023China AI Department Suzhou Alphama Biotechnology Co.Ltd.Suzhou 215000China Shanghai Institute for Advanced Immunochemical Studies and School of Life Science and TechnologyShanghaiTech UniversityShanghai 200031China State Key Laboratory of Pharmaceutical Biotechnology Nanjing UniversityNanjing 210023China

Aldehyde oxidase(AOX)is a molybdoenzyme that is primarily expressed in the liver and is involved in the metabolism of drugs and other ***-mediated metabolism can result in unexpected outcomes,such as the production of toxic metabolites and high metabolic clearance,which can lead to the clinical failure of novel therapeutic *** models can assist medicinal chemists in rapidly evaluating the AOX metabolic risk of compounds during the early phases of drug discovery and provide valuable clues for manipulating AOX-mediated metabolism *** this study,we developed a novel graph neural network called AOMP for predicting AOX-mediated *** integrated the tasks of metabolic substrate/non-substrate classification and metabolic site prediction,while utilizing transfer learning from 13C nuclear magnetic resonance data to enhance its performance on both *** significantly outperformed the benchmark methods in both cross-validation and external *** AOMP,we systematically assessed the AOX-mediated metabolism of common fragments in kinase inhibitors and successfully identified four new scaffolds with AOX metabolism liability,which were validated through in vitro ***,for the convenience of the community,we established the first online service for AOX metabolism prediction based on AOMP,which is freely available at https://***.

关键词： Drugmetabolism Aldehyde oxidase Transferlearning graph neural network Kinase inhibitor

BGNN: Behavior-aware graph neural network for heterogeneous session-based recommendation

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第5期17卷 103-118页

作者： Jinwei LUO Mingkai HE Weike PAN Zhong MING College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060China National Engineering Laboratory for Big Data System Computing Technology Shenzhen UniversityShenzhen 518060China

Session-based recommendation(SBR)and multibehavior recommendation(MBR)are both important problems and have attracted the attention of many researchers and *** from SBR that solely uses one single type of behavior sequences and MBR that neglects sequential dynamics,heterogeneous SBR(HSBR)that exploits different types of behavioral information(e.g.,examinations like clicks or browses,purchases,adds-to-carts and adds-to-favorites)in sequences is more consistent with real-world recommendation scenarios,but it is rarely *** efforts towards HSBR focus on distinguishing different types of behaviors or exploiting homogeneous behavior transitions in a sequence with the same type of ***,all the existing solutions for HSBR do not exploit the rich heterogeneous behavior transitions in an explicit way and thus may fail to capture the semantic relations between different types of ***,all the existing solutions for HSBR do not model the rich heterogeneous behavior transitions in the form of graphs and thus may fail to capture the semantic relations between different types of *** limitation hinders the development of HSBR and results in unsatisfactory *** a response,we propose a novel behavior-aware graph neural network(BGNN)for *** BGNN adopts a dual-channel learning strategy for differentiated modeling of two different types of behavior sequences in a ***,our BGNN integrates the information of both homogeneous behavior transitions and heterogeneous behavior transitions in a unified *** then conduct extensive empirical studies on three real-world datasets,and find that our BGNN outperforms the best baseline by 21.87%,18.49%,and 37.16%on average correspondingly.A series of further experiments and visualization studies demonstrate the rationality and effectiveness of our *** exploratory study on extending our BGNN to handle more than two types of behaviors show that our BGNN can e

关键词： session-based recommendation graph neural network heterogeneous behaviors

Residual Convolutional graph neural network with Subgraph Attention Pooling

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2022年第4期27卷 653-663页

作者： Yutai Duan Jianming Wang Haoran Ma Yukuan Sun Information and Communication Engineering Department Tiangong UniversityTianjin 300387China Computer Science Department Tiangong UniversityTianjin 300387China Software Engineering Department Tiangong UniversityTianjin 300387China Center for Engineering Intership and Training Tiangong UniversityTianjin 300387China

The pooling operation is used in graph classification tasks to leverage hierarchical structures preserved in data and reduce computational ***,pooling shrinkage discards graph details,and existing pooling methods may lead to the loss of key classification *** this work,we propose a residual convolutional graph neural network to tackle the problem of key classification features ***,our contributions are threefold:(1)Different from existing methods,we propose a new strategy to calculate sorting values and verify their importance for graph *** strategy does not only use features of simple nodes but also their neighbors for the accurate evaluation of its importance.(2)We design a new graph convolutional layer architecture with the residual *** feeding discarded features back into the network architecture,we reduce the probability of losing critical features for graph classification.(3)We propose a new method for graph-level *** messages for each node are aggregated separately,and then different attention levels are assigned to each node and merged into a graph-level representation to retain structural and critical information for *** experimental results show that our method leads to state-of-the-art results on multiple graph classification benchmarks.

关键词： graph neural network graph pooling information loss

Deep hybrid: Multi-graph neural network collaboration for hyperspectral image classification

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2023年第5期23卷 164-176页

作者： Ding Yao Zhang Zhi-li Zhao Xiao-feng Cai Wei He Fang Cai Yao-ming Wei-Wei Cai Xi'an Research Institute of High Technology Xi'an710025China The School of Computer Science China University of GeosciencesWuhan430074China The School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi214122China

With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current *** graph neural network(GNN)has emerged as an approach to semi-supervised classification,and the application of GNN to hyperspectral images has attracted much ***,in the existing GNN-based methods a single graph neural network or graph filter is mainly used to extract HSI features,which does not take full advantage of various graph neural networks(graph filters).Moreover,the traditional GNNs have the problem of *** alleviate these shortcomings,we introduce a deep hybrid multi-graph neural network(DHMG),where two different graph filters,i.e.,the spectral filter and the autoregressive moving average(ARMA)filter,are utilized in two *** former can well extract the spectral features of the nodes,and the latter has a good suppression effect on graph *** network realizes information interaction between the two branches and takes good advantage of different graph *** addition,to address the problem of oversmoothing,a dense network is proposed,where the local graph features are *** dense structure satisfies the needs of different classification targets presenting different ***,we introduce a graphSAGEbased network to refine the graph features produced by the deep hybrid *** experiments on three public HSI datasets strongly demonstrate that the DHMG dramatically outperforms the state-ofthe-art models.

关键词： graph neural network Hyperspectral image classification Deep hybrid network

Log Anomaly Detection Based on Hierarchical graph neural network and Label Contrastive Coding

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第2期74卷 4099-4118页

作者： Yong Fang Zhiying Zhao Yijia Xu Zhonglin Liu School of Cyber Science and Engineering Sichuan UniversityChengdu610000China

System logs are essential for detecting anomalies,querying faults,and tracing *** of the time-consuming and labor-intensive nature of manual system troubleshooting and anomaly detection,it cannot meet the actual *** implementation of automated log anomaly detection is a topic that demands urgent ***,the prior work on processing log data is mainly one-dimensional and cannot profoundly learn the complex associations in log ***,there is a lack of attention to the utilization of log labels and usually relies on a large number of labels for *** paper proposes a novel and practical detection model named LCC-HGLog,the core of which is the conversion of log anomaly detection into a graph classification *** temporal graphs(STG)are constructed by extracting the raw logs’execution sequences and template *** a unique graph classifier is used to better comprehend each STG’s semantic,sequential,and structural *** classification model is trained jointly by graph classification loss and label contrastive *** achieving discriminability at the class-level,it increases the fine-grained identification at the instance-level,thus achieving detection performance even with a small amount of labeled *** have conducted numerous experiments on real log datasets,showing that the proposed model outperforms the baseline methods and obtains the best all-around ***,the detection performance degrades to less than 1%when only 10%of the labeled data is *** 200 labeled samples,we can achieve the same or better detection results than the baseline methods.

关键词： Log analysis anomaly detection contrastive learning graph neural network