检索结果-南通市图书馆

A novel graph oversampling framework for node classification in class-imbalanced graphs

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第6期67卷 214-229页

作者： Riting XIA Chunxu ZHANG Yan ZHANG Xueyan LIU Bo YANG Key laboratory of symbolic computation and knowledge engineering of Ministry of Education Jilin University College of Artificial Intelligence Jilin University College of Computer Science and Technology Jilin University College of Communication engineering Jilin University

Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling. In this paper, we propose a novel graph oversampling framework, termed distribution alignment-based oversampling for node classification in classimbalanced graphs(named Graph-DAO). Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs. Additionally, we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes. To our best knowledge, it is the first to use the sum-product network to solve the class-imbalanced problem in node classification. A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.

关键词： graph neural network class-imbalanced graphs sum-product network oversampling node classification

同方期刊数据库

A Novel Locomotion Rule Rmbedding Long Short-Term Memory Network with Attention for Human Locomotor Intent Classification Using Multi-Sensors Signals

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4349-4370页

作者： Jiajie Shen Yan Wang Dongxu Zhang Key laboratory of Symbol computation and knowledge engineering Ministry of EducationColleague of Computer Science and TechnologyJilin UniversityChangchun130012China College of Software and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchun130012China

Locomotor intent classification has become a research hotspot due to its importance to the development of assistive robotics and wearable *** work have achieved impressive performance in classifying steady locomotion ***,it remains challenging for these methods to attain high accuracy when facing transitions between steady locomotion *** to the similarities between the information of the transitions and their adjacent steady ***,most of these methods rely solely on data and overlook the objective laws between physical activities,resulting in lower accuracy,particularly when encountering complex locomotion modes such as *** address the existing deficiencies,we propose the locomotion rule embedding long short-term memory(LSTM)network with Attention(LREAL)for human locomotor intent classification,with a particular focus on transitions,using data from fewer sensors(two inertial measurement units and four goniometers).The LREAL network consists of two levels:One responsible for distinguishing between steady states and transitions,and the other for the accurate identification of locomotor *** classifier in these levels is composed of multiple-LSTM layers and an attention *** introduce real-world motion rules and apply constraints to the network,a prior knowledge was added to the network via a rule-modulating *** method was tested on the ENABL3S dataset,which contains continuous locomotion date for seven steady and twelve transitions *** results showed that the LREAL network could recognize locomotor intents with an average accuracy of 99.03%and 96.52%for the steady and transitions states,*** is worth noting that the LREAL network accuracy for transition-state recognition improved by 0.18%compared to other state-of-the-art network,while using data from fewer sensors.

关键词： Lower-limb prosthetics deep neural networks motion classification

DeciLS-PBO: an effective local search method for pseudo-Boolean 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

Frontiers of Computer Science 2024年第2期18卷 239-241页

作者： Luyu JIANG Dantong OUYANG Qi ZHANG Liming ZHANG College of Computer Science and Technology Jilin UniversityChangchun 130012China Key laboratory of symbolic computation and knowledge engineering(Ministry of Education) Jilin UniversityChangchun 130012China

1 Introduction Local search method is a rising star for solving combinatorial optimization problems in recent years,and the state-of-the-art local search-based incomplete Maximum Satisfiability(MaxSAT)solversshowpromi... 详细信息

关键词： Max optimization local

Measuring drug similarity using drug–drug interactions

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

Quantitative Biology 2024年第2期12卷 164-172页

作者： Ji Lv Guixia Liu Yuan Ju Houhou Huang Ying Sun College of Computer Science and Technology Jilin UniversityChangchunChina Key laboratory of symbolic computation and knowledge engineering of Ministry of Education Jilin UniversityChangchunChina Sichuan University Library Sichuan UniversityChengduChina College of Chemistry Jilin UniversityChangchunChina Department of Respiratory Medicine The First Hospital of Jilin UniversityChangchunChina

Combination therapy is a promising approach to address the challenge of antimicrobial resistance,and computational models have been proposed for predicting drug–drug *** existing models rely on drug similarity measures based on characteristics such as chemical structure and the mechanism of *** this study,we focus on the network structure itself and propose a drug similarity measure based on drug–drug interaction *** explore the potential applications of this measure by combining it with unsupervised learning and semi-supervised learning *** unsupervised learning,drugs can be grouped based on their interactions,leading to almost monochromatic group–group *** addition,drugs within the same group tend to have similar mechanisms of action(MoA).In semi-supervised learning,the similarity measure can be utilized to construct affinity matrices,enabling the prediction of unknown drug–drug *** method exceeds existing approaches in terms of ***,our experiments demonstrate the effectiveness and practicability of the proposed similarity *** the one hand,when combined with clustering algorithms,it can be used for functional annotation of compounds with unknown *** the other hand,when combined with semi-supervised graph learning,it enables the prediction of unknown drug–drug interactions.

关键词： drug similarity drug–drug interactions drug combinations synergy effect clustering semi-supervised learning

DiagDO: an efficient model based diagnosis approach with multiple observations

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第6期17卷 125-134页

作者： Huisi ZHOU Dantong OUYANG Xinliang TIAN Liming ZHANG laboratory of symbolic computation and knowledge engineering Jilin UniversityChangchun 130000China College of Computer Science and Technology Jilin UniversityChangchun 130000China

Model-based diagnosis(MBD)with multiple observations shows its significance in identifying fault *** existing approaches for MBD with multiple observations use observations which is inconsistent with the prediction of the *** this paper,we proposed a novel diagnosis approach,namely,the Diagnosis with Different Observations(DiagDO),to exploit the diagnosis when given a set of pseudo normal observations and a set of abnormal *** ideas are proposed in this ***,for each pseudo normal observation,we propagate the value of system inputs and gain fanin-free edges to shrink the size of possible faulty ***,for each abnormal observation,we utilize filtered nodes to seek surely normal ***,we encode all the surely normal components and parts of dominated components into hard clauses and compute diagnosis using the MaxSAT solver and MCS *** tests on the ISCAS'85 and ITC'99 benchmarks show that our approach performs better than the state-of-the-art algorithms.

关键词： model based diagnosis maximum satisfiability top-level diagnosis cardinality-minimal diagnosis subset-minimal diagnosis

Lightweight axiom pinpointing via replicated driver and customized SAT-solving

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第2期17卷 121-133页

作者： Dantong OUYANG Mengting LIAO Yuxin YE College of Computer Science and Technology Jilin UniversityChangchun 130012China Key laboratory of symbolic computation and knowledge engineering(Jilin University) Ministry of EducationChangchun 130012China

In description logic,axiom pinpointing is used to explore defects in ontologies and identify hidden justifications for a logical *** recent years,SAT-based axiom pinpointing techniques,which rely on the enumeration of minimal unsatisfiable subsets(MUSes)of pinpointing formulas,have gained increasing *** with traditional Tableau-based reasoning approaches,SAT-based techniques are more competitive when computing justifications for consequences in large-scale lightweight description logic *** this article,we propose a novel enumeration justification algorithm,working with a replicated *** replicated driver discovers new justifications from the explored justifications through cheap literals resolution,which avoids frequent calls of SAT ***,when the use of SAT solver is inevitable,we adjust the strategies and heuristic parameters of the built-in SAT solver of axiom pinpointing *** adjusted SAT solver is able to improve the checking efficiency of unexplored *** proposed method is implemented as a tool named *** experimental results show that RDMinA outperforms the existing axiom pinpointing tools on practical biomedical ontologies such as Gene,Galen,NCI and Snomed-CT.

关键词： axiom pinpointing description logic SAT solver

Gradient sparsification for efficient wireless federated learning with differential privacy

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 272-288页

作者： Kang WEI Jun LI Chuan MA Ming DING Feng SHU Haitao ZHAO Wen CHEN Hongbo ZHU School of Electronic and Optical engineering Nanjing University of Science and Technology Zhejiang lab Key laboratory of Computer Network and Information Integration(Southeast University) Ministry of Education Data61 Commonwealth Scientific and Industrial Research Organisation School of Information and Communication engineering Hainan University School of Communications and Information engineering Nanjing University of Posts and Telecommunications School of Electronic Information and Electrical engineering Shanghai Jiao Tong University

Federated learning(FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers from the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to the limited transmission bandwidth and model performance degradation while using differential privacy(DP)protection. In this paper, we propose a gradient sparsification empowered FL framework with DP over wireless channels, to improve training efficiency without sacrificing convergence performance. Specifically, we first design a random sparsification algorithm to retain a fraction of the gradient elements in each client’s local model, thereby mitigating the performance degradation induced by DP and reducing the number of transmission parameters over wireless channels. Then, we analyze the convergence bound of the proposed algorithm, by modeling a non-convex FL problem. Next, we formulate a time-sequential stochastic optimization problem for minimizing the developed convergence bound, under the constraints of transmit power, the average transmitting delay, as well as the client’s DP requirement. Utilizing the Lyapunov drift-plus-penalty framework, we develop an analytical solution to the optimization problem. Extensive experiments have been implemented on three real-life datasets to demonstrate the effectiveness of our proposed algorithm. We show that our proposed algorithms can fully exploit the interworking between communication and computation to outperform the baselines, i.e., random scheduling, round robin, and delay-minimization algorithms.

关键词： federated learning differential privacy gradient sparsification Lyapunov drift convergence analysis

同方期刊数据库

Two-dimensional magnetic materials for spintronic applications

在线全文

学校读者我要写书评

暂无评论

Nano Research 2024年第2期17卷 743-762页

作者： Shivam N.Kajale Jad Hanna Kyuho Jang Deblina Sarkar MIT Media lab Massachusetts Institute of TechnologyCambridgeMA 02139USA Department of Information Technology and Electrical engineering ETH ZürichZürich8092Switzerland

Spintronic devices are driving new paradigms of bio-inspired,energy efficient computation like neuromorphic stochastic computing and in-memory *** have also emerged as key candidates for non-volatile memories for embedded systems as well as alternatives to persistent *** meet the growing demands from such diverse applications,there is need for innovation in materials and device designs which can be scaled and adapted according to the ***-dimensional(2D)magnetic materials address challenges facing bulk magnet systems by offering scalability while maintaining device integrity and allowing efficient control of *** this review,we highlight the progress made in experimental studies on 2D magnetic materials towards their integration into spintronic *** provide an account of the various relevant material discoveries,demonstrations of current and voltage-based control of magnetism and reported device systems,while also discussing the challenges and opportunities towards integration of 2D magnetic materials in commercial spintronic devices.

关键词： spintronics van der Waals magnetic tunnel junction(MTJ) spin-orbit torque magnetism

Dialectic operator fuzzy logic

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(Technological Sciences) 1996年第1期39卷 1-10页

作者：程晓春姜云飞刘叙华 open lab for symbolic computation and knowledge engineering Department of Computer ScienceJilin UniversityChangchun 130023China

Dialectic operator fuzzy logic (DOFL) is presented which is relevant,paraconsistent and *** can vividly describe the belief revision in the cognitive process and can infer reasonably well while the knowledge is incons... 详细信息

关键词： operator fuzzy logic relevant logic nonmonotonic logic paraconsistent logic.