Article
Computer Science, Information Systems
Shunjie Yuan, Hefeng Zeng, Ziyang Zuo, Chao Wang
Summary: This study proposes an overlapping community detection method CDMG based on Graph Convolutional Networks (GCN) to maximize the Markov stability of community structure. Extensive experiments demonstrate the superiority of CDMG compared to other established community detection algorithms. The performance of CDMG can be further improved by utilizing the optimal Markov time, which is found using a trichotomy-based method based on the influence of Markov time on CDMG performance.
COMPUTER COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Zhe Chen, Aixin Sun, Xiaokui Xiao
Summary: The article introduces an incremental community detection framework inc-AGGMMR, which maps attributes into the network by constructing an augmented graph and balances the contribution between attribute and topological information through weight adjustment.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2021)
Article
Computer Science, Artificial Intelligence
Hongtao Liu, Jiahao Wei, Tianyi Xu
Summary: In this paper, a new community detection method called CPGC is proposed, which combines the community perspective and graph convolution network to address the challenges of overlapping communities in attributed networks. CPGC achieves state-of-the-art results in nonoverlapping or overlapping communities, as demonstrated by experiments on various real-world networks.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Vincenzo Moscato, Giancarlo Sperli
Summary: Detecting users' communities in Online Social Networks is crucial for enhancing the effectiveness of diffusion of new ideas, improving recommendation suggestions, and finding experts. Different community detection techniques based on game theory, artificial intelligence, and fuzzy strategies are compared for various OSN models, highlighting pros and cons. Challenges and open issues in the community detection problem are discussed for future research.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Cybernetics
Ebin Deni Raj, Gunasekaran Manogaran, Gautam Srivastava, Yulei Wu
Summary: This article introduces an algorithm for detecting communities in online social networks, proposing a new algorithm named granular-based community detection. The algorithm is evaluated on real-world datasets and computer-generated datasets, outperforming other state-of-the-art community detection algorithms.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2021)
Article
Automation & Control Systems
Yansen Su, Chunlong Liu, Yunyun Niu, Fan Cheng, Xingyi Zhang
Summary: The research introduces a community structure enhancement method, CSE, which enhances the community structure of a network by adding links between nodes possibly belonging to the same community and reducing links between those belonging to different communities, thereby making the ambiguous community structure clearer. The experimental results demonstrate the superior performance of CSE over five state-of-the-art community detection algorithms on both synthetic benchmark networks and real-world networks, especially for those without a clear community structure.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Review
Computer Science, Information Systems
Norah Alotaibi, Delel Rhouma
Summary: This article provides an overview of the characteristics and challenges of community detection in dynamic social networks, and compares state-of-the-art methods. Researchers can use this survey to find the best methods and choose relevant future directions.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Aniello De Santo, Antonio Galli, Vincenzo Moscato, Giancarlo Sperli
Summary: This paper introduces an innovative approach for semi-supervised community detection using Convolutional Neural Networks, optimizing computational cost and outperforming existing techniques on large datasets in terms of running time and F1 scores.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Physics, Multidisciplinary
Jiating Yu, Jiacheng Leng, Duanchen Sun, Ling-Yun Wu
Summary: Network models are widely used in various fields for their ability to represent relationships between variables. Network structure can be unclear due to factors like experimental noise and missing data, hindering downstream analyses such as community detection. Therefore, network denoising is necessary before analysis. However, the importance of network pre-processing for community detection has been neglected. In this study, a novel network denoising method, called Network Refinement (NR), was proposed to enhance the self-organization properties of complex networks through a global diffusion process. NR significantly improved the clarity of the network's mesoscale structure and boosted the performance of various community detection algorithms.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Sanjay Kumar, B. S. Panda, Deepanshu Aggarwal
Summary: The paper introduces a new method for community detection using network embedding technique, embedding nodes into d-dimensional feature space and applying low-rank approximation and clustering algorithm to improve cluster centroids and detection effectiveness, evaluating the detected communities' effectiveness using various performance measures.
JOURNAL OF INTELLIGENT INFORMATION SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Stephany Rajeh, Marinette Savonnet, Eric Leclercq, Hocine Cherifi
Summary: This paper investigates the relationship between traditional centrality measures and community-aware centrality measures, showing that the latter perform better in networks with stronger community structures. Network transitivity and community structure strength are identified as the most significant drivers controlling the interactions between classical and community-aware centrality measures.
SCIENTIFIC REPORTS
(2021)
Article
Physics, Multidisciplinary
Iqra Erum, Rauf Ahmed Shams Malick, Ghufran Ahmed, Hocine Cherifi
Summary: This research utilizes digital event datasets to study mass killings, identifies influential actors and their dominant roles in the network, and suggests that removing these actors may help prevent the spread of conflict events.
Article
Computer Science, Cybernetics
Chaobo He, Xiang Fei, Qiwei Cheng, Hanchao Li, Zeng Hu, Yong Tang
Summary: Community detection is a popular research topic in complex networks analysis, with nonnegative matrix factorization (NMF) being an ideal model for this purpose. This article provides a comprehensive review of NMF-based methods for community detection, categorizing them based on network types and proposing potential research directions. Overall, the versatility of NMF-based community detection is highlighted as a useful guideline for researchers in related fields.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Amit Paul, Animesh Dutta
Summary: Detecting communities in complex networks is a challenging task due to their unknown properties. In this study, a Local Group Assimilation (LGA) algorithm is proposed to identify clusters or communities in a network graph using both local and global structure information. The algorithm achieves promising results in detecting significant communities in real networks and compares favorably to other state-of-the-art algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Sanjay Kumar, Abhishek Mallik, Sandeep Singh Sengar
Summary: This paper proposes a deep learning approach for community detection in complex networks, combining stacked autoencoders and the Crow Search Algorithm. Experimental results demonstrate that the proposed method achieves excellent performance.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Computer Science, Hardware & Architecture
Xiaoyang Liu, Shanghong Dai, Giacomo Fiumara, Pasquale De Meo
Summary: This article introduces a novel method for target-specific sentiment classification, which constructs an adversarial learning-based classification model by replacing synonyms and inserting random words. Experimental results demonstrate that this method improves classification performance and the capability of adversarial sample defense across multiple datasets.
Article
Mathematics
Annamaria Ficara, Francesco Curreri, Giacomo Fiumara, Pasquale De Meo, Antonio Liotta
Summary: This study examines covert networks, such as terrorist networks and criminal networks, using social network analysis (SNA). SNA helps identify the structure and functioning of these networks by calculating relevant metrics and parameters, enabling the identification of roles, positions, features, and other network characteristics. Law enforcement agencies are increasingly interested in SNA for identifying vulnerabilities and disrupting criminal groups. However, there are challenges in data collection techniques and the incompleteness and biases of real-world datasets.
Article
Engineering, Multidisciplinary
Lucia Cavallaro, Stefania Costantini, Pasquale De Meo, Antonio Liotta, Giovanni Stilo
Summary: This paper examines the impact of node removal on network robustness, proposes a probabilistic node failure model considering node strength, conducts experimental analysis on 8 real-world graphs, and finds that degree is the most significant factor causing the drop in spectral radius and the size of the largest connected component.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Xiaoyang Liu, Xiang Li, Giacomo Fiumara, Pasquale De Meo
Summary: This paper proposes a link prediction approach that combines Graph Neural Networks (GNNs) with Capsule Networks (CapsNet). The method transforms node embeddings into a node pair feature map and uses CapsNets to learn the feature representation, achieving better accuracy than competitor methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Cybernetics
Xiaoyang Liu, Shu Ye, Giacomo Fiumara, Pasquale De Meo
Summary: This article proposes a hybrid method based on K-shell decomposition to identify the most influential spreaders in complex networks. The method combines K-shell decomposition with existing centrality methods, and selects the most influential nodes based on comprehensive scores. Experimental results show significant improvements in infection scale and shortest path length.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Albert Matuozzo, Paul D. Yoo, Alessandro Provetti
Summary: This study uses a variety of predictors, including a lagged and transformed version of the target series, to predict the future returns of the STOXX Europe 600 and the German DAX based on time series analysis. Feature engineering is employed to extract knowledge of market conditions and demand for hedging. By introducing a penalisation factor and loss functions, a traditional machine learning regression framework is adapted to solve equity forecasting problems using neural networks. Architecture based on convolutional neural network is proposed, treating the obtained feature map similar to an image. Experiments demonstrate that trading strategies derived from these forecasts are more profitable than those based on efficient market assumptions, indicating the importance of considering the temporal, non-stationary structure of financial data.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Pasquale De Meo, Mark Levene, Alessandro Provetti
Summary: The article introduces a variant of the branching process model, which can be used to predict the popularity of user-generated content and rank search results or suggestions. A new centrality index called the Stochastic Potential Gain (SPG) is proposed to evaluate the importance of agents in a social network. Experimental results demonstrate the effectiveness of this method in computing node centrality measures for online social networks.
INFORMATION SCIENCES
(2023)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Lucia Cavallaro, Pasquale De Meo, Keyvan Golalipour, Xiaoyang Liu, Giacomo Fiumara, Andrea Tagarelli, Antonio Liotta
Summary: This study aims to explore the impact of small graph perturbations on centrality metrics. It is found that in the Uniform model, the change in the adjacency matrix is not significant when nodes are under small-scale attacks, even with a high failure probability. However, in the Best Connected model, the degree of perturbation is proportional to the ratio of nodes under attack.
COMPLEX NETWORKS AND THEIR APPLICATIONS XI, COMPLEX NETWORKS 2022, VOL 2
(2023)
Article
Computer Science, Theory & Methods
Annamaria Ficara, Francesco Curreri, Giacomo Fiumara, Pasquale De Meo
Summary: Social Network Analysis (SNA) is used to analyze criminal networks and develop disruption interventions and crime prevention systems. This paper investigates the effectiveness of seven disruption strategies for real Mafia networks using SNA tools. Simulations show that actor removal based on social capital is the most effective strategy in disrupting criminal networks. Removing specific figures of Mafia families, like the Caporegime, also shows promise.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Computer Science, Cybernetics
Xiaoyang Liu, Chenxiang Miao, Giacomo Fiumara, Pasquale De Meo
Summary: With the development of deep learning and other technologies, the proposed spatial-temporal attention heterogeneous graph convolutional networks (STAHGCNs) model has greatly improved the accuracy of information propagation prediction by integrating spatial factors such as time factor, user influence, and behavior. The experimental results have shown significant improvements over the original latest DyHGCN model in hits@N and map@N by 8.80% and 6.74% respectively, demonstrating the effectiveness of the proposed model. It has great significance for rumor monitoring and malicious account detection.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Hardware & Architecture
Flavia Bonomo-Braberman, Nick Brettell, Andrea Munaro, Daniel Paulusma
Summary: This article discusses the convexity and mim-width of bipartite graphs, and it proves that for certain families of graphs 7-t, the 7-t-convex graphs can be solved in polynomial time for NP-complete problems. It also explores the bounded and unbounded mim-width of 7-t-convex graphs for different sets 7-t.
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
(2024)
Article
Computer Science, Hardware & Architecture
Keqin Li
Summary: In this paper, we propose a computation offloading strategy to satisfy all UEs served by an MEC and develop an efficient method to find such a strategy. By using Markov chains to characterize UE mobility and calculating the joint probability distribution of UE locations, we can obtain the average response time of UEs and predict the overall average response time of tasks. Additionally, we solve the power constrained MEC speed setting problem.
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
(2024)
Correction
Computer Science, Hardware & Architecture
Peter L. Bartlett, Philip M. Long
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
(2024)
Article
Computer Science, Hardware & Architecture
Philipp Czerner, Roland Guttenberg, Martin Helfrich, Javier Esparza
Summary: This paper presents a construction method that produces population protocols with a small number of states, while achieving near-optimal expected number of interactions, for deciding Presburger predicates.
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
(2024)
Article
Computer Science, Hardware & Architecture
Katharina T. Huber, Leo van Iersel, Remie Janssen, Mark Jones, Vincent Moulton, Yukihiro Murakami, Charles Semple
Summary: This paper investigates the relationship between undirected and directed phylogenetic networks, and provides corresponding algorithms. The study reveals that the directed phylogenetic network is unique under specific conditions. Additionally, an algorithm for directing undirected binary networks is described, applicable to certain classes of directed phylogenetic networks.
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
(2024)
Article
Computer Science, Hardware & Architecture
Francesco Betti Sorbelli, Alfredo Navarra, Lorenzo Palazzetti, Cristina M. Pinotti, Giuseppe Prencipe
Summary: This study discusses the deployment of IoT sensors in an area that needs to be monitored. Drones are used to collect data from the sensors, but they have energy and storage constraints. To maximize the overall reward from the collected data and ensure compliance with energy and storage limits, an optimization problem called Multiple-drone Data-collection Maximization Problem (MDMP) is proposed and solved using an Integer Linear Programming algorithm.
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
(2024)
Article
Computer Science, Hardware & Architecture
Carla Binucci, Emilio Di Giacomo, William J. Lenhart, Giuseppe Liotta, Fabrizio Montecchiani, Martin Nollenburg, Antonios Symvonis
Summary: In this study, we investigate the problem of representing a graph as a storyplan, which is a model for dynamic graph visualization. We prove the NP-completeness of this problem and propose two parameterized algorithms as solutions. We also demonstrate that partial 3-trees always admit a storyplan and can be computed in linear time. Additionally, we show that even if the vertex appearance order is given, the problem of choosing how to draw the frames remains NP-complete.
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
(2024)
Article
Computer Science, Hardware & Architecture
Leszek Gasieniec, Tomasz Jurdzinski, Ralf Klasing, Christos Levcopoulos, Andrzej Lingas, Jie Min, Tomasz Radzik
Summary: This passage describes the Bamboo Garden Trimming Problem and presents approximation algorithms for both Discrete BGT and Continuous BGT.
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
(2024)