Article
Computer Science, Information Systems
Phu Pham, Loan T T Nguyen, Bay Vo, Unil Yun
Summary: Due to the rapid growth of online social networks, the number of machine accounts/social bots has increased, prompting the need for reliable bot detection mechanisms to keep OSNs safe. The proposed Bot2Vec model utilizes network representation learning to automatically retain local neighborhood relations and user community structures, without relying on user profile features. By employing intra-community random walk strategy, Bot2Vec aims to outperform existing network embedding baselines for bot detection tasks. Extensive experiments on Twitter and Tagged networks demonstrate the effectiveness of the proposed model.
INFORMATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Boyu Li, Meng Wang, John E. Hopcroft, Kun He
Summary: This article introduces the importance of multiple local community detection and proposes an algorithm called HoSIM based on higher-order structural importance. HoSIM measures the importance score between nodes using Active Random Walk and evaluates the importance score of a subgraph to a node and the importance score of a node with two new metrics. Experiments demonstrate the effectiveness of HoSIM.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Makoto Okuda, Shinichi Satoh, Yoichi Sato, Yutaka Kidawara
Summary: The paper proposes a method for detecting community structures of graphs by restraining random walk similarity. The method judges starting vertices as being in the same community if the random walkers pass similar sets of vertices. Experimental results demonstrate that the method outperforms previous techniques in terms of accuracy.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
Ying Yin, Yuhai Zhao, He Li, Xiangjun Dong
Summary: The paper proposes an efficient and effective multi-objective method, DYN-MODPSO, which addresses the issues in dynamic community detection by enhancing the traditional evolutionary clustering framework and particle swarm algorithm. The novel strategy and carefully designed operators contribute to the method's superior performance on both real and synthetic dynamic networks, outperforming competitors in terms of effectiveness and efficiency.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Kun Guo, Qinze Wang, Jiaqi Lin, Ling Wu, Wenzhong Guo, Kuo-Ming Chao
Summary: This paper proposes a network representation learning based algorithm for overlapping community detection, which improves the cohesion of similar nodes by integrating community information into embedding vectors. The algorithm automatically determines the parameters for random walk and uses community-aware random walk strategies to capture the characteristics of communities.
APPLIED INTELLIGENCE
(2022)
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
Christian Toth, Denis Helic, Bernhard C. Geiger
Summary: This paper presents Synwalk, a random walk-based community detection method, which detects communities in networks by synthesizing random walks. The results indicate that Synwalk performs robustly in various network scenarios.
DATA MINING AND KNOWLEDGE DISCOVERY
(2022)
Article
Computer Science, Artificial Intelligence
Kun Guo, Peng Zhang, Wenzhong Guo, Yuzhong Chen
Summary: This paper presents a novel attentional-walk-based autoencoder (AWBA) that integrates random walk with attentional coefficients to mine high-order relationships between nodes, aiming to improve community detection. Experimental results demonstrate the superior performance of our algorithm compared to baseline algorithms.
APPLIED INTELLIGENCE
(2023)
Article
Telecommunications
Makhlouf Benazi, Bilal Lounnas, Rabah Mokhtari
Summary: In this article, we propose a novel algorithm based on a modified random walk and label propagation algorithm for discovering communities in complex networks. Experimental results show that our algorithm outperforms existing methods.
TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES
(2022)
Article
Computer Science, Artificial Intelligence
Yang Gao, Xiangzhan Yu, Hongli Zhang
Summary: Local community detection methods aim at finding communities around initial nodes in a network, addressing efficiency problems faced by global clustering methods. Techniques like personalized PageRank and heat kernel diffusion are used to rank proximity scores of vertices nearby.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Yang Chang, Huifang Ma, Liang Chang, Zhixin Li
Summary: Community detection methods based on random walks are widely used in network analysis tasks. However, in real-world networks, nodes have different attributes, which make the detection more challenging. To address this issue, the paper proposes a community detection method called CAS based on attributed random walk, which is demonstrated to be effective through experiments.
FRONTIERS OF COMPUTER SCIENCE
(2022)
Article
Statistics & Probability
Tianxi Li, Lihua Lei, Sharmodeep Bhattacharyya, Koen Van den Berge, Purnamrita Sarkar, Peter J. Bickel, Elizaveta Levina
Summary: The problem of community detection in networks is usually formulated as finding a single partition of the network into correct number of communities. However, constructing a hierarchical tree of communities is more interpretable and accurate in some cases. A top-down recursive partitioning algorithm can be used to separate nodes into communities by spectral clustering repeatedly, until no further communities are suggested by a stopping rule. This model-free and computationally efficient algorithm outperforms K-way spectral clustering in certain regimes.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2022)
Article
Computer Science, Information Systems
Qingqing Li, Huifang Ma, Ju Li, Zhixin Li, Liang Chang
Summary: Community search aims to efficiently search high-quality communities in networks using sample nodes. We propose a novel multi-community search method in attributed networks that combines complex structural relationship and attribute information to effectively search for multiple communities where sample nodes are located. The proposed method utilizes similarity enhanced random walk to reinforce the walking paths of sample nodes and identifies densely connected and similar attribute communities using parallel conductance.
INFORMATION SCIENCES
(2023)
Article
Physics, Multidisciplinary
Qian Liu, Jian Wang, Zhidan Zhao, Na Zhao
Summary: In this paper, a relatively important nodes mining algorithm based on community detection and biased random walk with restart (CDBRWR) is proposed. The algorithm incorporates community information into the mining of relatively important nodes, and introduces a new biased random walk strategy with restart to achieve accurate and efficient mining. Experimental verification and analysis show that the CDBRWR algorithm outperforms other comparative algorithms in terms of precision, recall, and AUC.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2022)
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
Operations Research & Management Science
Chuangen Gao, Shuyang Gu, Jiguo Yu, Hai Du, Weili Wu
Summary: This paper discusses the benefits of interactions among activated nodes in social networks and proposes an adaptive seeding strategy for profit maximization. The study introduces an adaptive sandwich policy for an approximation solution based on the sandwich strategy. The effectiveness of the proposed algorithm is verified through real data sets.
JOURNAL OF GLOBAL OPTIMIZATION
(2022)
Article
Computer Science, Theory & Methods
Guoyao Rao, Yongcai Wang, Wenping Chen, Deying Li, Weili Wu
Summary: Online social networks have had a profound impact on our lives, leading to an increase in research on social influence. Previous studies on social influence have primarily focused on individual influence, but in many cases, influencing an important group can bring greater profits than directly influencing individuals. We propose a model called the Union Acceptable Profit Problem (UAPM) to maximize the probability of a union being acceptable and present efficient estimation methods and algorithms to solve the problem. We evaluate the performance of our algorithms using real-world social network datasets.
THEORETICAL COMPUTER SCIENCE
(2022)
Article
Mathematics
Lin Zhang, Kan Li
Summary: In this study, a novel framework called Influence Maximization based on Prediction and Replacement (IMPR) is proposed to address the influence maximization problem in dynamic online social networks. The framework utilizes historical network snapshot information to predict upcoming network snapshots, and employs a fast replacement algorithm to solve the seed node problem. Experimental results demonstrate the promising performance of the proposed scheme.
Article
Engineering, Multidisciplinary
Qiufen Ni, Jianxiong Guo, Weili Wu, Huan Wang, Jigang Wu
Summary: Community partition is crucial in social networks, particularly in the face of network growth and increased data and applications. This study focuses on the community partition problem under the Linear Threshold (LT) model, aiming to maximize influence propagation within each community. The proposed continuous greedy algorithm, which exploits the properties of the relaxed function, is able to effectively improve influence spread and accuracy of the community partition. Theoretical analysis demonstrates a 1 - 1/e approximation ratio for the algorithm, while extensive experiments on real-world online social networks datasets validate its performance.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Review
Mathematics, Applied
Priyanshi Garg, Weili Wu
Summary: This paper explores the use of social media in generating Online Social Networks (OSNs) and the various research tasks associated with them, such as community detection, link prediction, and influence modeling. Different models for modeling influence diffusion processes are discussed, and the applications of influence maximization and rumor blocking in different scenarios are examined. The concept of viral marketing is also explored.
DISCRETE MATHEMATICS ALGORITHMS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Zhichao Ma, Kan Li, Yang Li
Summary: This article introduces a self-supervised method that can train a 3D human pose estimation network without any extra 3D pose annotations. By fully disentangling the camera viewpoint information and 3D human shape, the method overcomes the projection ambiguity problem and utilizes a hierarchical dictionary for stable canonical reconstruction.
APPLIED INTELLIGENCE
(2023)
Review
Mathematics, Applied
Tiantian Chen, Jianxiong Guo, Weili Wu
Summary: Online social platforms have grown rapidly in the past decade and play a crucial role in communication and information sharing. Understanding the mechanisms and consequences of information diffusion is important for viral marketing and advertising. The development of neural networks has led to more effective graph representation learning methods.
DISCRETE MATHEMATICS ALGORITHMS AND APPLICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Jianxiong Guo, Xingjian Ding, Weili Wu
Summary: Real-time traffic monitoring is essential in smart cities for understanding traffic conditions and preventing accidents. This article proposes a reliable and efficient traffic monitoring system that integrates blockchain and IoT technologies, crowdsourcing tasks to vehicles. The system includes a lightweight blockchain-based information trading framework and auction mechanism to incentivize vehicle participation and ensure budget constraints. Numerical simulations confirm the reliability and efficiency of the framework and algorithms.
IEEE TRANSACTIONS ON RELIABILITY
(2022)
Article
Automation & Control Systems
Jianxiong Guo, Weili Wu
Summary: This study addresses the revenue maximization problem in social networks, utilizing adaptive seeding strategies and a collaboration game model to compute revenue based on user activities. It introduces the RM problem under size and community budget constraints, and proposes RMSBSolver and RMCBSolver to address the problems in various scenarios with theoretical guarantees. Additionally, data-dependent approximation ratios are provided for general nonsubmodular cases, and the effectiveness and accuracy of the solutions are demonstrated through experiments on real datasets.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Computer Science, Information Systems
Tiantian Chen, Jianxiong Guo, Weili Wu
Summary: Online social networks are important platforms for viral marketing, but existing research mainly focuses on the diffusion of products with single features. However, in reality, products may have multiple features that spread independently. Based on this, we propose the multi-feature budgeted profit maximization problem and consider adaptive models for solving it. We conduct experiments to compare our proposed strategies with existing ones, and the results demonstrate the efficiency and superiority of our approaches.
SOCIAL NETWORK ANALYSIS AND MINING
(2022)
Article
Computer Science, Artificial Intelligence
Shengdong Li, Chuanwen Luo, Yuqing Zhu, Weili Wu
Summary: Stacked attention networks (SANs) are a classic model for visual question answering (VQA) and have effectively promoted research progress in VQA. This paper proposes a method called bold driver and static restart fused adaptive momentum (BDSRM) to optimize SANs, by fusing bold driver and static restart (BDSR) into momentum. The experiments demonstrate that BDSRM outperforms state-of-the-art optimization algorithms on SANs.
KNOWLEDGE AND INFORMATION SYSTEMS
(2023)
Article
Computer Science, Cybernetics
Qiufen Ni, Jianxiong Guo, Weili Wu, Huan Wang
Summary: This article focuses on the community partition problem in social networks and formulates it as a combinatorial optimization problem. Continuous greedy algorithms and discrete implementations are proposed to solve the upper and lower bound problems, achieving a good approximation ratio. The effectiveness and advantages of the proposed method are demonstrated through experiments on real datasets.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Yiwei Li, Shaoxiong Feng, Bin Sun, Kan Li
Summary: The paper introduces a novel negative training paradigm called negative distillation to address the generic response problem in generative dialogue models. By introducing a negative teacher model and requiring the student model to maximize the distance with multi-level negative knowledge, the method significantly improves upon previous negative training approaches.
NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Shaoxiong Feng, Xuancheng Ren, Kan Li, Xu Sun
Summary: In this work, a hierarchical inductive transfer framework is proposed to learn and deploy dialogue skills continually and efficiently. By introducing adapter modules and using general knowledge in the base adapter to alleviate knowledge interference between tasks, the framework achieves comparable performance on embedded devices.
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022)
(2022)
Article
Telecommunications
Jianxiong Guo, Xingjian Ding, Weili Wu
Summary: With the development of smart cities, a large distributed network has been formed between cities, which raises the challenge of secure and efficient energy trading. In this paper, a blockchain-based multiple energies trading system is proposed, using a smart contract and a new byzantine-based consensus mechanism. The model and algorithms are validated using numerical simulations, demonstrating their correctness and efficiency.
IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING
(2022)
Article
Computer Science, Artificial Intelligence
Hao Yang, Min Wang, Zhengfei Yu, Hang Zhang, Jinshen Jiang, Yun Zhou
Summary: In this paper, a novel method called CSTTA is proposed for test time adaptation (TTA), which utilizes confidence-based optimization and sample reweighting to better utilize sample information. Extensive experiments demonstrate the effectiveness of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Jin Liu, Ju-Sheng Mi, Dong-Yun Niu
Summary: This article focuses on a novel method for generating a canonical basis for decision implications based on object-induced operators (OE operators). The logic of decision implication based on OE operators is described, and a method for obtaining the canonical basis for decision implications is given. The completeness, nonredundancy, and optimality of the canonical basis are proven. Additionally, a method for generating true premises based on OE operators is proposed.
KNOWLEDGE-BASED SYSTEMS
(2024)
Review
Computer Science, Artificial Intelligence
Kun Bu, Yuanchao Liu, Xiaolong Ju
Summary: This paper discusses the importance of sentiment analysis and pre-trained models in natural language processing, and explores the application of prompt learning. The research shows that prompt learning is more suitable for sentiment analysis tasks and can achieve good performance.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangjun Cai, Dagang Li
Summary: This paper presents a new decomposition mechanism based on learned decomposition mapping. By using a neural network to learn the relationship between original time series and decomposed results, the repetitive computation overhead during rolling decomposition is relieved. Additionally, extended mapping and partial decomposition methods are proposed to alleviate boundary effects on prediction performance. Comparative studies demonstrate that the proposed method outperforms existing RDEMs in terms of operation speed and prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xu Wu, Yang Liu, Jie Tian, Yuanpeng Li
Summary: This paper proposes a blockchain-based privacy-preserving trust management architecture, which adopts federated learning to train task-specific trust models and utilizes differential privacy to protect device privacy. In addition, a game theory-based incentive mechanism and a parallel consensus protocol are proposed to improve the accuracy of trust computing and the efficiency of consensus.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zaiyang Yu, Prayag Tiwari, Luyang Hou, Lusi Li, Weijun Li, Limin Jiang, Xin Ning
Summary: This study introduces a 3D view-based approach that effectively handles occlusions and leverages the geometric information of 3D objects. The proposed method achieves state-of-the-art results on occluded ReID tasks and exhibits competitive performance on holistic ReID tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Yongliang Shi, Runyi Yang, Zirui Wu, Pengfei Li, Caiyun Liu, Hao Zhao, Guyue Zhou
Summary: Neural implicit representations have gained attention due to their expressive, continuous, and compact properties. However, there is still a lack of research on city-scale continual implicit dense mapping based on sparse LiDAR input. In this study, a city-scale continual neural mapping system with a panoptic representation is developed, incorporating environment-level and instance-level modeling. A tailored three-layer sampling strategy and category-specific prior are proposed to address the challenges of representing geometric information in city-scale space and achieving high fidelity mapping of instances under incomplete observation.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ruihan Hu, Zhi-Ri Tang, Rui Yang, Zhongjie Wang
Summary: Mesh data is crucial for 3D computer vision applications worldwide, but traditional deep learning frameworks have struggled with handling meshes. This paper proposes MDSSN, a simple mesh computation framework that models triangle meshes and represents their shape using face-based and edge-based Riemannian graphs. The framework incorporates end-to-end operators inspired by traditional deep learning frameworks, and includes dedicated modules for addressing challenges in mesh classification and segmentation tasks. Experimental results demonstrate that MDSSN outperforms other state-of-the-art approaches.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Buliao Huang, Yunhui Zhu, Muhammad Usman, Huanhuan Chen
Summary: This paper proposes a novel semi-supervised conditional normalizing flow (SSCFlow) algorithm that combines unsupervised imputation and supervised classification. By estimating the conditional distribution of incomplete instances, SSCFlow facilitates imputation and classification simultaneously, addressing the issue of separated tasks ignoring data distribution and label information in traditional methods.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Junchen Ye, Weimiao Li, Zhixin Zhang, Tongyu Zhu, Leilei Sun, Bowen Du
Summary: Modeling multivariate time series has long been a topic of interest for scholars in various fields. This paper introduces MvTS, an open library based on Pytorch, which provides a unified framework for implementing and evaluating these models. Extensive experiments on public datasets demonstrate the effectiveness and universality of the models reproduced by MvTS.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Reham R. Mostafa, Ahmed M. Khedr, Zaher Al Aghbari, Imad Afyouni, Ibrahim Kamel, Naveed Ahmed
Summary: Feature selection is crucial in classification procedures, but it faces challenges in high-dimensional datasets. To overcome these challenges, this study proposes an Adaptive Hybrid-Mutated Differential Evolution method that incorporates the mechanics of the Spider Wasp Optimization algorithm and the concept of Enhanced Solution Quality. Experimental results demonstrate the effectiveness of the method in terms of accuracy and convergence speed, and it outperforms contemporary cutting-edge algorithms.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ti Xiang, Pin Lv, Liguo Sun, Yipu Yang, Jiuwu Hao
Summary: This paper introduces a Track Classification Model (TCM) based on marine radar, which can effectively recognize and classify shipping tracks. By using a feature extraction network with multi-feature fusion and a dataset production method to address missing labels, the classification accuracy is improved, resulting in successful engineering application in real scenarios.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zhihao Zhang, Yuan Zuo, Chenghua Lin, Junjie Wu
Summary: This paper proposes a novel unsupervised context-aware quality phrase mining framework called LMPhrase, which is built upon large pre-trained language models. The framework mines quality phrases as silver labels using a parameter-free probing technique on the pre-trained language model BERT, and formalizes the phrase tagging task as a sequence generation problem by fine-tuning on the Sequence to-Sequence pre-trained language model BART. The results of extensive experiments show that LMPhrase consistently outperforms existing competitors in two different granularity phrase mining tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Kemal Buyukkaya, M. Ozan Karsavuran, Cevdet Aykanat
Summary: The study aims to investigate the hybrid parallelization of the Stochastic Gradient Descent (SGD) algorithm for solving the matrix completion problem on a high-performance computing platform. A hybrid parallel decentralized SGD framework with asynchronous inter-process communication and a novel flexible partitioning scheme is proposed to achieve scalability up to hundreds of processors. Experimental results on real-world benchmark datasets show that the proposed algorithm achieves 6x higher throughput on sparse datasets compared to the state-of-the-art, while achieving comparable throughput on relatively dense datasets.
KNOWLEDGE-BASED SYSTEMS
(2024)