检索结果-内蒙古大学图书馆

Integrating a Sequential Model Into GNN-Based Social Recommendation for Relieving Over-Smoothing Problem

IEEE Access 2025年 13卷 100219-100233页

作者： Janekhwan Kitsupapaisan Saranya Maneeroj Atsuhiro Takasu Department of Mathematics and Computer Science Faculty of Science Advanced Virtual and Intelligent Computing Center Chulalongkorn University Bangkok Thailand National Institute of Informatics Tokyo Japan

In recent years, social recommendation systems have increasingly integrated Graph Neural Networks (GNNs) to capture social relationships among users from both direct and higher-order neighbors. However, these state-of-the-art models face limitations regarding the number of iterations they can propagate across the graph. Messages from higher-order neighbors often dilute the unique characteristics of the target node. This causes node representations to become similar and indistinguishable, leading to a phenomenon known as the over-smoothing problem. Several works have attempted to address this problem with the expectation of preserving user characteristics. They add auxiliary information to the GNN-based social recommendation models without considering the dynamic preferences of users, which frequently change over time. Therefore, those works still struggle with the same problem after propagating in a few iterations. To mitigate this phenomenon, we propose a novel approach to integrate user characteristics extracted from users’ historical interactions using a sequential model to slow down node convergence. Integrating user characteristics into the GNN-based social recommendation will allow the model to capture user preferences that dynamically change over time. Consequently, the proposed model will be able to leverage informative data from higher-order neighbors over social networks for user representation learning, leading to better performance and effectiveness of the recommendations. Our experimental results demonstrate that the proposed model outperforms state-of-the-art social recommendation models across three benchmark datasets.

关键词： Representation learning Graph neural networks Social networking (online) Convergence Redundancy Recommender systems Diffusion processes Smoothing methods Nickel Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Two-Tier Anomaly-based Intrusion Detection Approach for IoT-Enabled Smart Cities

A Two-Tier Anomaly-based Intrusion Detection Approach for Io...

引用

2023 IEEE INFOCOM Conference on computer Communications Workshops, INFOCOM WKSHPS 2023

作者： Hamdan, Mosab Eldhai, Arwa M. Abdelsalam, Samah Ullah, Kifayat Bashir, Ali Kashif Marsono, M.N. Kon, Fabio Batista, Daniel Macêdo Department of Computer Science Brazil University of Science and Technology Faculty of Engineering Sudan Khartoum University Faculty of Mathematical Sciences and Informatics Sudan Manchester Metropolitan University Department of Computing and Mathematics United Kingdom Universiti Teknologi Malaysia Faculty of Electrical Engineering Malaysia

ISBN: (纸本)9781665494274

The Internet of Things (IoT), like other network infrastructures, requires Intrusion Detection Systems (IDSs) to be protected against attacks. When deploying an IDS in IoT-based smart city environments, the balance between latency and node capacity must be considered, which justifies a distributed IDS with specific classifiers based on the location of the system processing nodes. This paper proposes a two-level classification technique for collaborative anomaly-based IDSs deployed on fog and edge nodes. A Gradient Boosting Classifier (GBC) is used in the lower layer classifier at the edge, while a Convolutional Neural Network (CNN) is used in the upper layer classifier at the fog. Experimentation has demonstrated that the suggested IDS architecture outperforms previous solutions. For instance, in some scenarios, when comparing our proposal with Random Forest, the former obtained an accuracy equal to 99.1%, while the latter obtained 95.3%. Furthermore, our proposal can better select the most important network traffic features, reducing 76% of the data to be analyzed and improving privacy. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Cost-Effective HWIL testing methodology for SALS guided missiles

引用

Materials Today: Proceedings 2022年 62卷 2509-2515页

作者： Todi, Ivana Kuzmanovi, Vladimir University of Belgrade Faculty of Mechanical Engineering Weapon Systems Department Kraljice Marije 16 Belgrade 11120 Serbia University of Belgrade Faculty of Mathematics Department for Computer Science and Informatics Studentski Trg 16 Belgrade 11000 Serbia

Verifying a new missile design requires a series of successful real-life tests on a firing range in various scenarios. Such an approach is extremely expensive and requires complex infrastructure and logistics. The costs of developing a new missile design can be significantly reduced by applying extensive and well thought out laboratory testing prior to any real-life test. Laboratory tests such as Hardware-In-The-Loop (HWIL) simulation enable the missile to be tested in a controlled environment inside a laboratory. HWIL testing methodology enables engineers to test the missile or its components in various simulated scenarios that correspond to real-life flights. Usually, a five-axis motion platform is used to perform HWIL simulation of terminal guidance. Three inner axes of the five-axis motion platform are used for simulation of the missiles body angles, while the two outer axes are used for simulation of the target movement relative to the missile. Such an approach requires spacious laboratories and expensive equipment. In this paper, we present a cost-effective HWIL testing methodology for Semi-Active-Laser-Seeker (SALS) guided missiles. The presented methodology requires only a three-axis motion platform and a fixed laser source. In the paper, we propose a two-stage HWIL testing procedure. In the first stage, the INS algorithm, guidance algorithm and autopilot algorithms are verified. In the second stage of the proposed HWIL testing methodology, the terminal guidance algorithm based on SALS angles is verified. Besides the HWIL testing methodology, we present the guidance law used in the testing procedure as well as the design of intercommunication between all the devices required to perform the tests. Next, the obtained results after each stage of the proposed HWIL testing methodology are presented and analyzed. Finally, a conclusion is drawn and limitations of the proposed testing methodology are explained. © 2020

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Corrigendum: The diameter of AT-free graphs

引用

Journal of Graph Theory 2024年第4期107卷 848-850页

作者： Guillaume Ducoffe National Institute for Research and Development in Informatics Bucharest Romania Faculty of Mathematics and Computer Science University of Bucharest Bucharest Romania

This corrigendum corrects an error found in the proof of correctness of the algorithm by [Ducoffe, JGT, 2022, 99(4), pp. 594–614], Theorem 6. An erroneous result from Deogun and Kratsch was used in the original proof... 详细信息

关键词： AT-free graphs chordal graphs dominating pairs fine-grained complexity in P

来源：评论

学校读者我要写书评

暂无评论

A STUDY ON SOME CLASSES OF PANTOGRAPH LANGEVIN FRACTIONAL DIFFERENTIAL PROBLEMS WITH NONLOCAL CONDITIONS

引用

Journal of Mathematical sciences (United States) 2025年 1-18页

作者： Bouzid, Houari Benali, Abdelkader Salim, Abdelkrim Erhan, İnci M. Department of Mathematics Faculty of Exact Science and Informatics Laboratory of Mathematics and Applications (LMA) Hassiba Benbouali University of Chlef Ouled Fares Chlef 02000 Algeria Faculty of Technology Hassiba Benbouali University of Chlef Chlef 02000 Algeria Laboratory of Mathematics Djillali Liabes University of Sidi Bel-Abbes Sidi Bel-Abbes 22000 Algeria Department of Computer Engineering Aydın Adnan Menderes University Aydın 09010 Turkey

This paper concentrates on the examination of a class of nonlocal initial value problems for Langevin fractional differential equations featuring the ψ-Caputo fractional derivative within Banach spaces. By utilizing Banach’s fixed-point theorem, we establish the uniqueness of the solutions to these problems. The existence of solutions is then confirmed using Schaefer’s and Darbo’s fixed-point theorems. Finally, we provide examples to illustrate our findings. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Darbo theorem Fractional differential equations (FDE) Measure of noncompactness ψ-fractional integral

来源：评论

学校读者我要写书评

暂无评论

Standardized feature extraction from pairwise conflicts applied to the train rescheduling problem 20

Standardized feature extraction from pairwise conflicts appl...

引用

20th IEEE Jubilee World Symposium on Applied Machine Intelligence and informatics, SAMI 2022

作者： Kopacz, Aniko Mester, Agnes Kolumban, Sandor Csato, Lehel Babeş-Bolyai University Faculty of Mathematics and Computer Science Cluj-Napoca Romania Institute of Applied Informatics and Applied Mathematics Óbuda University Budapest Hungary

ISBN: (纸本)9781665497046

We propose a train rescheduling algorithm which applies a standardized feature selection based on pairwise conflicts in order to serve as input for the reinforcement learning framework. We implement an analytical method which identifies and optimally solves every conflict arising between two trains, then we design a corresponding observation space which features the most relevant information considering these conflicts. The data obtained this way then translates to actions in the context of the reinforcement learning framework. We test our preliminary model using the evaluation metrics of the Flatland Challenge. The empirical results indicate that the suggested feature space provides meaningful observations, from which a sensible scheduling policy can be learned. © 2022 IEEE.

关键词： Measurement Reinforcement learning Feature extraction informatics Machine intelligence

来源：评论

学校读者我要写书评

暂无评论

Blocked Bloom Filters with Choices

arXiv

引用

arXiv 2025年

作者： Schmitz, Johanna Elena Zentgraf, Jens Rahmann, Sven Faculty of Mathematics and Computer Science Saarland University Saarbrücken Graduate School of Computer Science Center for Bioinformatics Saar Saarland Informatics Campus Saarbrücken Germany Faculty of Mathematics and Computer Science Saarland University Center for Bioinformatics Saar Saarland Informatics Campus Saarbrücken Germany

Probabilistic filters are approximate set membership data structures that represent a set of keys in small space, and answer set membership queries without false negative answers, but with a certain allowed false positive probability. Such filters are widely used in database systems, networks, storage systems and in biological sequence analysis because of their fast query times and low space requirements. Starting with Bloom filters in the 1970s, many filter data structures have been developed, each with its own advantages and disadvantages, e.g., Blocked Bloom filters, Cuckoo filters, XOR filters, Ribbon filters, and more. We introduce Blocked Bloom filters with choices that work similarly to Blocked Bloom filters, except that for each key there are two (or more) alternative choices of blocks where the key’s information may be stored. The result is a filter that partially inherits the advantages of a Blocked Bloom filter, such as the ability to insert keys rapidly online or the ability to slightly overload the filter with only a small penalty to the false positive rate. At the same time, it avoids the major disadvantage of a Blocked Bloom filter, namely the larger space consumption. Our new data structure uses less space at the same false positive rate, or has a lower false positive rate at the same space consumption as a Blocked Bloom filter. We discuss the methodology, engineered implementation, a detailed performance evaluation and use cases in bioinformatics of Blocked Bloom filters with choices, showing that they can be of practical value. The implementation of the evaluated filters and the workflows used are provided via Gitlab at https://***/rahmannlab/blowchoc-filters. © 2025, CC BY.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

A language for graph database evolution and its implementation in Neo4j 42

A language for graph database evolution and its implementati...

引用

42nd International Conference on Conceptual Modeling: ER Forum, 7th Symposium on Conceptual Modeling Education, SCME 2023, Project Exhibitions, Posters and Demos, and Doctoral Consortium, ER-Companion 2023

作者： Hausler, Dominique Klettke, Meike Störl, Uta University of Regensburg Data Engineering Group Faculty of Informatics and Data Science Bajuwarenstrasse 4 Regensburg93053 Germany University of Hagen Chair of Databases and Information Systems Faculty of Mathematics and Computer Science Universitätsstrasse 1 Hagen58084 Germany

In this article, we present an evolution language for graph databases and a method to realize evolution operations on graph databases and their schema. Graph database management systems like Neo4j can be used for different scenarios: they can store graphs where no semantic constraints are checked. It is also possible to use them to store graphs where the structure of nodes and relationships is regular, for example, because the nodes and relationships of a graph have been generated by an application. In the latter case, these structures may change, that means they can undergo evolution. Currently, there is no established evolutionary language for graphs. However, evolution operations (such as add, rename, delete, merge, copy, split and move) have already been developed for other database models. In this article, we will not only use the established evolution operations but additionally extend the operations appropriated. After analyzing evolution operators explicitly in the context of graph databases, we also created a new graph-specific operation: transform. Moreover, we suggest an evolution language to graph data and show how it can be executed on the graph database schema as well as on the instances (i.e. the graphs themselves). In doing so, some operations can be implemented native based on Cypher, others non-native using the APOC library for Neo4j. © 2023 CEUR-WS. All rights reserved.

关键词： evolution graph databases evolution graph evolution language graph schema description

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey of Data Reduction Rules for the Maximum Weighted Independent Set Problem

arXiv

引用

arXiv 2024年

作者： Großmann, Ernestine Langedal, Kenneth Schulz, Christian Heidelberg University Faculty of Mathematics and Computer Science Germany University of Bergen Department of Informatics Norway

The Maximum Weight Independent Set (MWIS) problem, as well as its related problems such as Minimum Weight Vertex Cover, are fundamental NP-hard problems with numerous practical applications. Due to their computational complexity, a variety of data reduction rules have been proposed in recent years to simplify instances of these problems, enabling exact solvers and heuristics to handle them more effectively. Data reduction rules are polynomial time procedures that can reduce an instance while ensuring that an optimal solution on the reduced instance can be easily extended to an optimal solution for the original instance. Data reduction rules have proven to be especially useful in branch-and-reduce methods, where successful reductions often lead to problem instances that can be solved exactly. This survey provides a comprehensive overview of data reduction rules for the MWIS problem. We also provide a reference implementation for these reductions. This survey will be updated as new reduction techniques are developed, serving as a centralized resource for researchers and practitioners © 2024, CC BY.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Accelerating Reductions Using Graph Neural Networks and a New Concurrent Local Search for the Maximum Weight Independent Set Problem

arXiv

引用

arXiv 2024年

作者： Großmann, Ernestine Langedal, Kenneth Schulz, Christian Heidelberg University Faculty of Mathematics and Computer Science Germany University of Bergen Department of Informatics Norway

The Maximum Weight Independent Set problem is a fundamental NP-hard problem in combinatorial optimization with several real-world applications. Given an undirected vertex-weighted graph, the problem is to find a subset of the vertices with the highest possible weight under the constraint that no two vertices in the set can share an edge. An important part of solving this problem in both theory and practice is data reduction rules, which several state-of-the-art algorithms rely on. However, the most complicated rules are often not used in applications since the time needed to check them exhaustively becomes infeasible. In this work, we introduce three main results. First, we introduce several new data reduction rules and evaluate their effectiveness on real-world data. Second, we use a machine learning screening algorithm to speed up the reduction phase, thereby enabling more complicated rules to be applied. Our screening algorithm consults a Graph Neural Network oracle to decide if the probability of successfully reducing the graph is sufficiently large. For this task, we provide a dataset of labeled vertices for use in supervised learning. We also present the first results for this dataset using established Graph Neural Network architectures. Third, we present a new concurrent metaheuristic called Concurrent Difference-Core Heuristic. On the reduced instances, we use our new metaheuristic combined with iterated local search, called CHILS (Concurrent Hybrid Iterated Local Search). For this iterated local search, we provide a new implementation specifically designed to handle large graphs of varying densities. CHILS outperforms the current state-of-the-art on all commonly used benchmark instances, especially the largest ones. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：