Pub Date : 2024-08-14DOI: 10.1109/TAI.2024.3443789
Fok Hing Chi Tivive;Abdesselam Bouzerdoum;Son Lam Phung;Hoang Thanh Le;Hamza Baali
Image-based crowd counting has gained significant attention due to its widespread applications in security and surveillance. Recent advancements in deep learning have led to the development of numerous methods that have achieved remarkable success in accurately counting crowds. However, many of the existing deep learning methods, which have large model sizes, are unsuitable for deployment on edge devices. This article introduces a novel network architecture and processing element designed to create an efficient and compact deep learning model for crowd counting. The processing element, referred to as the shunting inhibitory neuron, generates complex decision boundaries, making it more powerful than the traditional perceptron. It is employed in both the encoder and decoder modules of the proposed model for feature extraction. Furthermore, the decoder includes alternating convolutional and transformer layers, which provide local receptive fields and global self-attention, respectively. This design captures rich contextual information that is used for generating accurate segmentation and density maps. The self-attention mechanism is implemented using convolution modulation instead of matrix multiplication to reduce computational costs. Experiments conducted on three challenging crowd counting datasets demonstrate that the proposed deep learning network, which comprises a small model size, achieves crowd counting performance comparable to that of state-of-the-art techniques. Codes are available at https://github.com/ftivive/SINet .
{"title":"A Deep Learning-Based Method for Crowd Counting Using Shunting Inhibition Mechanism","authors":"Fok Hing Chi Tivive;Abdesselam Bouzerdoum;Son Lam Phung;Hoang Thanh Le;Hamza Baali","doi":"10.1109/TAI.2024.3443789","DOIUrl":"https://doi.org/10.1109/TAI.2024.3443789","url":null,"abstract":"Image-based crowd counting has gained significant attention due to its widespread applications in security and surveillance. Recent advancements in deep learning have led to the development of numerous methods that have achieved remarkable success in accurately counting crowds. However, many of the existing deep learning methods, which have large model sizes, are unsuitable for deployment on edge devices. This article introduces a novel network architecture and processing element designed to create an efficient and compact deep learning model for crowd counting. The processing element, referred to as the shunting inhibitory neuron, generates complex decision boundaries, making it more powerful than the traditional perceptron. It is employed in both the encoder and decoder modules of the proposed model for feature extraction. Furthermore, the decoder includes alternating convolutional and transformer layers, which provide local receptive fields and global self-attention, respectively. This design captures rich contextual information that is used for generating accurate segmentation and density maps. The self-attention mechanism is implemented using convolution modulation instead of matrix multiplication to reduce computational costs. Experiments conducted on three challenging crowd counting datasets demonstrate that the proposed deep learning network, which comprises a small model size, achieves crowd counting performance comparable to that of state-of-the-art techniques. Codes are available at \u0000<uri>https://github.com/ftivive/SINet</uri>\u0000.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5733-5745"},"PeriodicalIF":0.0,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-14DOI: 10.1109/TAI.2024.3443787
Amandeep Kaur
The rapid growth of industrial Internet of Things (IIoT) applications generates massive amount of heterogeneous data that are prone to cyberattacks. The imperative is to secure industrial data from adversarial attacks and develop a robust and secure framework capable of withstanding sophisticated attacks. Toward this machine learning (ML) algorithms are used for intrusion detection by analyzing the devices’ network traffic. However, classical ML models work on entire datasets that are located on a central server and are not a suitable choice for a secure intrusion detection framework. We propose the federated learning (FL)-based network intrusion detection model for IIoT scenarios which only share learned parameters with the central server and keep the data intact to local servers only. The proposed model is assisted with gated recurrent units (GRUs) for FL training to extract temporal dependencies of network traffic attacks in order to improve intrusion detection accuracy. Additionally, to increase the model aggregation rate of FL, we integrate deep reinforcement learning (DRL) to select of IIoT devices with high quality while keeping data privacy and energy-efficiency as main concerns. In contrast to earlier approaches, we consider nonindependent and identically distributed (non-IID) data over recent IIoT datasets. Experimental findings indicate that the proposed framework outperforms state-of-the-art FL and non-FL intrusion detection models in terms of accuracy, precision, recall, F1-score, and receiver operating characterstics (ROC).
{"title":"Intrusion Detection Approach for Industrial Internet of Things Traffic Using Deep Recurrent Reinforcement Learning Assisted Federated Learning","authors":"Amandeep Kaur","doi":"10.1109/TAI.2024.3443787","DOIUrl":"https://doi.org/10.1109/TAI.2024.3443787","url":null,"abstract":"The rapid growth of industrial Internet of Things (IIoT) applications generates massive amount of heterogeneous data that are prone to cyberattacks. The imperative is to secure industrial data from adversarial attacks and develop a robust and secure framework capable of withstanding sophisticated attacks. Toward this machine learning (ML) algorithms are used for intrusion detection by analyzing the devices’ network traffic. However, classical ML models work on entire datasets that are located on a central server and are not a suitable choice for a secure intrusion detection framework. We propose the federated learning (FL)-based network intrusion detection model for IIoT scenarios which only share learned parameters with the central server and keep the data intact to local servers only. The proposed model is assisted with gated recurrent units (GRUs) for FL training to extract temporal dependencies of network traffic attacks in order to improve intrusion detection accuracy. Additionally, to increase the model aggregation rate of FL, we integrate deep reinforcement learning (DRL) to select of IIoT devices with high quality while keeping data privacy and energy-efficiency as main concerns. In contrast to earlier approaches, we consider nonindependent and identically distributed (non-IID) data over recent IIoT datasets. Experimental findings indicate that the proposed framework outperforms state-of-the-art FL and non-FL intrusion detection models in terms of accuracy, precision, recall, F1-score, and receiver operating characterstics (ROC).","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 1","pages":"37-50"},"PeriodicalIF":0.0,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-13DOI: 10.1109/TAI.2024.3443011
Yuan-Xin Li;Bo Xu;Xing-Yu Zhang
Artificial intelligence (AI) offers fuzzy logic system (FLS) technique as one of the popular AI agents and decision-making tools for control systems to deal with uncertain nonlinearities. This article is concerned with the event-triggered intelligent fuzzy adaptive stabilization of a class of reaction-diffusion systems based on parabolic partial differential equations-ordinary differential equations (PDE–ODEs). The studied system type is an ODE subsystem with nonlinear and unknown control coefficients for controlling PDEs. The original PDE is transformed into a new target system through the infinite-dimensional transformation method, and a state feedback controller for the transformed system is designed with the adaptive backstepping method to stabilize the system. An event-triggered strategy based on a relative threshold is designed into the backstepping framework. When the triggering condition of the system is met, the control signal of the ODE subsystem is updated. The designed control scheme ensures that all closed-loop signals are bounded; in addition, the original system states can converge to zero. Finally, the simulation example demonstrates that the event-triggered control (ETC)-based stability control technology has a good control effect.
{"title":"Event-Triggered Fuzzy Adaptive Stabilization of Parabolic PDE–ODE Systems","authors":"Yuan-Xin Li;Bo Xu;Xing-Yu Zhang","doi":"10.1109/TAI.2024.3443011","DOIUrl":"https://doi.org/10.1109/TAI.2024.3443011","url":null,"abstract":"Artificial intelligence (AI) offers fuzzy logic system (FLS) technique as one of the popular AI agents and decision-making tools for control systems to deal with uncertain nonlinearities. This article is concerned with the event-triggered intelligent fuzzy adaptive stabilization of a class of reaction-diffusion systems based on parabolic partial differential equations-ordinary differential equations (PDE–ODEs). The studied system type is an ODE subsystem with nonlinear and unknown control coefficients for controlling PDEs. The original PDE is transformed into a new target system through the infinite-dimensional transformation method, and a state feedback controller for the transformed system is designed with the adaptive backstepping method to stabilize the system. An event-triggered strategy based on a relative threshold is designed into the backstepping framework. When the triggering condition of the system is met, the control signal of the ODE subsystem is updated. The designed control scheme ensures that all closed-loop signals are bounded; in addition, the original system states can converge to zero. Finally, the simulation example demonstrates that the event-triggered control (ETC)-based stability control technology has a good control effect.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6580-6590"},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-13DOI: 10.1109/TAI.2024.3443004
Wenting Song;Shaocheng Tong
In this study, an optimal output feedback tracking control approach with a Q-learning algorithm is presented for Takagi–Sugeno (T–S) fuzzy discrete-time systems with immeasurable states. First, a state reconstruction method based on the measured output data and input data is applied to handle immeasurable states problem. Then, the optimal output feedback tracking control input policy is designed and boiled down to the algebraic Riccati equations (AREs). To obtain the solution to AREs, a Q-learning value iteration (VI) algorithm is formulated, which directly learns each state-action value. Consequently, the sufficient conditions for the convergence of the proposed optimal algorithm are derived by constructing an approximate Q-function. It is proved that the presented optimal output feedback tracking control method can guarantee the controlled systems to be stable and output track the given reference signal. Finally, we take the truck-trailer system as the simulation example, the simulation results validate feasibility of the presented optimal control methodology.
针对状态不可测的Takagi-Sugeno （T-S）模糊离散系统，提出了一种基于q学习算法的最优输出反馈跟踪控制方法。首先，采用一种基于测量输出数据和输入数据的状态重构方法来处理状态不可测问题。然后，设计了最优输出反馈跟踪控制输入策略，并将其归结为代数Riccati方程（AREs）。为了得到AREs的解，提出了一种q -学习值迭代（Q-learning value iteration， VI）算法，该算法直接学习每个状态-动作值。因此，通过构造一个近似的q函数，得到了该最优算法收敛的充分条件。实验证明，所提出的最优输出反馈跟踪控制方法能够保证被控系统稳定，输出跟踪给定参考信号。最后，以汽车挂车系统为例进行了仿真，仿真结果验证了所提出的最优控制方法的可行性。
{"title":"Optimal Output Feedback Tracking Control for Takagi–Sugeno Fuzzy Systems","authors":"Wenting Song;Shaocheng Tong","doi":"10.1109/TAI.2024.3443004","DOIUrl":"https://doi.org/10.1109/TAI.2024.3443004","url":null,"abstract":"In this study, an optimal output feedback tracking control approach with a Q-learning algorithm is presented for Takagi–Sugeno (T–S) fuzzy discrete-time systems with immeasurable states. First, a state reconstruction method based on the measured output data and input data is applied to handle immeasurable states problem. Then, the optimal output feedback tracking control input policy is designed and boiled down to the algebraic Riccati equations (AREs). To obtain the solution to AREs, a Q-learning value iteration (VI) algorithm is formulated, which directly learns each state-action value. Consequently, the sufficient conditions for the convergence of the proposed optimal algorithm are derived by constructing an approximate Q-function. It is proved that the presented optimal output feedback tracking control method can guarantee the controlled systems to be stable and output track the given reference signal. Finally, we take the truck-trailer system as the simulation example, the simulation results validate feasibility of the presented optimal control methodology.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6320-6329"},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-13DOI: 10.1109/TAI.2024.3442731
Xingsi Xue;Jerry Chun-Wei Lin;Tong Su
Ontology matching (OM) is critical for knowledge integration and system interoperability on the semantic web, tasked with identifying semantically related entities across different ontologies. Despite its importance, the complexity of terminology semantics and the large number of potential matches present significant challenges. Existing methods often struggle to balance between accurately capturing the multifaceted nature of semantic relationships and computational efficiency. This work introduces a novel approach, a compact multitasking multichromosome genetic algorithm for Heuristic selection (HS) in OM, designed to navigate the nuanced hierarchical structure of ontologies and diverse entity mapping preferences. Our method combines compact genetic algorithms with multichromosome optimization for entity sequencing and assigning HS, alongside an adaptive knowledge transfer mechanism to finely balance exploration and exploitation efforts. Evaluated on the ontology alignment evaluation initiative's benchmark, our algorithm demonstrates superior ability to produce high-quality ontology alignments efficiently, surpassing comparative methods in both effectiveness and efficiency. These findings underscore the potential of advanced genetic algorithms in enhancing OM processes, offering significant contributions to the broader AI field by improving the interoperability and knowledge integration capabilities of semantic web technologies.
本体匹配（OM）对于语义网络上的知识集成和系统互操作性至关重要，其任务是识别不同本体中语义相关的实体。尽管本体匹配非常重要，但术语语义的复杂性和大量潜在匹配却带来了巨大挑战。现有的方法往往难以在准确捕捉语义关系的多面性和计算效率之间取得平衡。这项工作介绍了一种新方法，即用于 OM 启发式选择（Heuristic selection，HS）的紧凑型多任务多染色体遗传算法，该算法旨在引导本体的细微分层结构和不同的实体映射偏好。我们的方法将紧凑型遗传算法与多染色体优化相结合，用于实体排序和分配启发式选择（HS），同时还采用了自适应知识转移机制，以微妙地平衡探索和利用工作。根据本体对齐评估计划的基准进行评估，我们的算法展示了高效生成高质量本体对齐的卓越能力，在有效性和效率方面都超过了其他方法。这些发现凸显了先进遗传算法在增强 OM 流程方面的潜力，通过提高语义网络技术的互操作性和知识整合能力，为更广泛的人工智能领域做出了重大贡献。
{"title":"Compact Multitasking Multichromosome Genetic Algorithm for Heuristic Selection in Ontology Matching","authors":"Xingsi Xue;Jerry Chun-Wei Lin;Tong Su","doi":"10.1109/TAI.2024.3442731","DOIUrl":"https://doi.org/10.1109/TAI.2024.3442731","url":null,"abstract":"Ontology matching (OM) is critical for knowledge integration and system interoperability on the semantic web, tasked with identifying semantically related entities across different ontologies. Despite its importance, the complexity of terminology semantics and the large number of potential matches present significant challenges. Existing methods often struggle to balance between accurately capturing the multifaceted nature of semantic relationships and computational efficiency. This work introduces a novel approach, a compact multitasking multichromosome genetic algorithm for Heuristic selection (HS) in OM, designed to navigate the nuanced hierarchical structure of ontologies and diverse entity mapping preferences. Our method combines compact genetic algorithms with multichromosome optimization for entity sequencing and assigning HS, alongside an adaptive knowledge transfer mechanism to finely balance exploration and exploitation efforts. Evaluated on the ontology alignment evaluation initiative's benchmark, our algorithm demonstrates superior ability to produce high-quality ontology alignments efficiently, surpassing comparative methods in both effectiveness and efficiency. These findings underscore the potential of advanced genetic algorithms in enhancing OM processes, offering significant contributions to the broader AI field by improving the interoperability and knowledge integration capabilities of semantic web technologies.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6752-6766"},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-13DOI: 10.1109/TAI.2024.3442153
Jun Fu;Yan Wang
Community detection is a fundamental and widely studied field in network science. To perform community detection, various competitive multiobjective evolutionary algorithms (MOEAs) have been proposed. It is worth noting that the latest continuous encoding (CE) method transforms the original discrete problem into a continuous one, which can achieve better community partitioning. However, the original CE ignored important structural features of nodes, such as the clustering coefficient (CC), resulting in poor initial solutions and reduced the performance of community detection. Therefore, we propose a simple scheme to effectively utilize node structure feature vectors to enhance community detection. Specifically, a CE and CC-based (CE-CC) MOEA called CECC-Net is proposed. In CECC-Net, the CC vector performs the Hadamard product with a continuous vector (i.e., a concatenation of the continuous variables $mathbf{x}$ associated with the edges), resulting in an improved initial individual. Then, applying the nonlinear transformation to the continuous-valued individual yields a discrete-valued community grouping solution. Furthermore, a corresponding adaptive operator is designed as an essential part of this scheme to mitigate the negative effects of feature vectors on population diversity. The effectiveness of the proposed scheme was validated through ablation and comparative experiments. Experimental results on synthetic and real-world networks demonstrate that the proposed algorithm has competitive performance in comparison with several state-of-the-art EA-based community detection algorithms.
社群检测是网络科学中的一个基础领域，也是一个被广泛研究的领域。为了进行社群检测，人们提出了各种有竞争力的多目标进化算法（MOEAs）。值得注意的是，最新的连续编码（CE）方法将原来的离散问题转化为连续问题，可以实现更好的社区划分。但是，原有的 CE 忽略了节点的重要结构特征，如聚类系数（CC），导致初始解不理想，降低了社区检测的性能。因此，我们提出了一种简单的方案，有效利用节点结构特征向量来增强社群检测。具体来说，我们提出了一种基于 CE 和 CC（CE-CC）的 MOEA，称为 CECC-Net。在 CECC-Net 中，CC 向量与连续向量（即与边缘相关的连续变量 $/mathbf{x}$）进行哈达玛乘积，从而得到一个改进的初始个体。然后，将非线性变换应用于连续值个体，就能得到离散值群体分组解决方案。此外，还设计了一个相应的自适应算子，作为该方案的重要组成部分，以减轻特征向量对群体多样性的负面影响。通过消融和对比实验，验证了所提方案的有效性。在合成网络和真实世界网络上的实验结果表明，与几种最先进的基于 EA 的群落检测算法相比，所提出的算法具有很强的竞争力。
{"title":"An Improved Continuous-Encoding-Based Multiobjective Evolutionary Algorithm for Community Detection in Complex Networks","authors":"Jun Fu;Yan Wang","doi":"10.1109/TAI.2024.3442153","DOIUrl":"https://doi.org/10.1109/TAI.2024.3442153","url":null,"abstract":"Community detection is a fundamental and widely studied field in network science. To perform community detection, various competitive multiobjective evolutionary algorithms (MOEAs) have been proposed. It is worth noting that the latest continuous encoding (CE) method transforms the original discrete problem into a continuous one, which can achieve better community partitioning. However, the original CE ignored important structural features of nodes, such as the clustering coefficient (CC), resulting in poor initial solutions and reduced the performance of community detection. Therefore, we propose a simple scheme to effectively utilize node structure feature vectors to enhance community detection. Specifically, a CE and CC-based (CE-CC) MOEA called CECC-Net is proposed. In CECC-Net, the CC vector performs the Hadamard product with a continuous vector (i.e., a concatenation of the continuous variables \u0000<inline-formula><tex-math>$mathbf{x}$</tex-math></inline-formula>\u0000 associated with the edges), resulting in an improved initial individual. Then, applying the nonlinear transformation to the continuous-valued individual yields a discrete-valued community grouping solution. Furthermore, a corresponding adaptive operator is designed as an essential part of this scheme to mitigate the negative effects of feature vectors on population diversity. The effectiveness of the proposed scheme was validated through ablation and comparative experiments. Experimental results on synthetic and real-world networks demonstrate that the proposed algorithm has competitive performance in comparison with several state-of-the-art EA-based community detection algorithms.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5815-5827"},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This research intends to address the critical need for precise brain tumor prediction through the development of an automated method that entwines the Firefly (FF) algorithm and the interval type-II fuzzy (IT2FLS) technique. The proposed method improves tumor delineation in complex brain tissue by using the FF algorithm to find possible cluster positions and the IT2FLS system for final clustering. This algorithm demonstrates its versatility by processing diverse image sequences from BRATS challenge datasets (2017, 2018, and 2020), which encompass varying levels of complexity. Through comprehensive evaluation metrics such as sensitivity, specificity, and dice-overlap index (DOI), the proposed algorithm consistently yields improved segmentation results. Ultimately, this research aims to augment oncologists' perceptual acumen, facilitating enhanced intuition and comprehension of patients' conditions, thereby advancing decision-making capabilities in medical research.
{"title":"Intelligent Multigrade Brain Tumor Identification in MRI: A Metaheuristic-Based Uncertain Set Framework","authors":"Saravanan Alagarsamy;Vishnuvarthanan Govindaraj;A. Shahina;D. Nagarajan","doi":"10.1109/TAI.2024.3441520","DOIUrl":"https://doi.org/10.1109/TAI.2024.3441520","url":null,"abstract":"This research intends to address the critical need for precise brain tumor prediction through the development of an automated method that entwines the Firefly (FF) algorithm and the interval type-II fuzzy (IT2FLS) technique. The proposed method improves tumor delineation in complex brain tissue by using the FF algorithm to find possible cluster positions and the IT2FLS system for final clustering. This algorithm demonstrates its versatility by processing diverse image sequences from BRATS challenge datasets (2017, 2018, and 2020), which encompass varying levels of complexity. Through comprehensive evaluation metrics such as sensitivity, specificity, and dice-overlap index (DOI), the proposed algorithm consistently yields improved segmentation results. Ultimately, this research aims to augment oncologists' perceptual acumen, facilitating enhanced intuition and comprehension of patients' conditions, thereby advancing decision-making capabilities in medical research.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5381-5391"},"PeriodicalIF":0.0,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-08DOI: 10.1109/TAI.2024.3440223
Jiaxu Liu;Xinping Yi;Xiaowei Huang
Hyperbolic graph convolutional networks (HGCNs) have demonstrated significant potential in extracting information from hierarchical graphs. However, existing HGCNs are limited to shallow architectures due to the computational expense of hyperbolic operations and the issue of oversmoothing as depth increases. Although treatments have been applied to alleviate oversmoothing in graph convolutional networks (GCNs), developing a hyperbolic solution presents distinct challenges since operations must be carefully designed to fit the hyperbolic nature. Addressing these challenges, we propose DeepHGCN, the first deep multilayer HGCN architecture with dramatically improved computational efficiency and substantially reduced oversmoothing. DeepHGCN features two key innovations: 1) a novel hyperbolic feature transformation layer that enables fast and accurate linear mappings; and 2) techniques such as hyperbolic residual connections and regularization for both weights and features, facilitated by an efficient hyperbolic midpoint method. Extensive experiments demonstrate that DeepHGCN achieves significant improvements in link prediction (LP) and node classification (NC) tasks compared to both Euclidean and shallow hyperbolic GCN variants.
{"title":"DeepHGCN: Toward Deeper Hyperbolic Graph Convolutional Networks","authors":"Jiaxu Liu;Xinping Yi;Xiaowei Huang","doi":"10.1109/TAI.2024.3440223","DOIUrl":"https://doi.org/10.1109/TAI.2024.3440223","url":null,"abstract":"Hyperbolic graph convolutional networks (HGCNs) have demonstrated significant potential in extracting information from hierarchical graphs. However, existing HGCNs are limited to shallow architectures due to the computational expense of hyperbolic operations and the issue of oversmoothing as depth increases. Although treatments have been applied to alleviate oversmoothing in graph convolutional networks (GCNs), developing a hyperbolic solution presents distinct challenges since operations must be carefully designed to fit the hyperbolic nature. Addressing these challenges, we propose DeepHGCN, the first deep multilayer HGCN architecture with dramatically improved computational efficiency and substantially reduced oversmoothing. DeepHGCN features two key innovations: 1) a novel hyperbolic feature transformation layer that enables fast and accurate linear mappings; and 2) techniques such as hyperbolic residual connections and regularization for both weights and features, facilitated by an efficient hyperbolic midpoint method. Extensive experiments demonstrate that DeepHGCN achieves significant improvements in link prediction (LP) and node classification (NC) tasks compared to both Euclidean and shallow hyperbolic GCN variants.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6172-6185"},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the times of advanced generative artificial intelligence, distinguishing truth from fallacy and deception has become a critical societal challenge. This research attempts to analyze the capabilities of large language models (LLMs) for detecting misinformation. Our study employs a versatile approach, covering multiple LLMs with few- and zero-shot prompting. These models are rigorously evaluated across various fake news and rumor detection datasets. Introducing a novel dimension, we additionally incorporate sentiment and emotion annotations to understand the emotional influence on misinformation detection using LLMs. Moreover, to extend our inquiry, we employ ChatGPT to intentionally distort authentic news as well as human-written fake news, utilizing zero-shot and iterative prompts. This deliberate corruption allows for a detailed examination of various parameters such as abstractness, concreteness, and named entity density, providing insights into differentiating between unaltered news, human-written fake news, and its LLM-corrupted counterpart. Our findings aspire to furnish a refined framework for discerning authentic news, human-generated misinformation, and LLM-induced distortions. This multifaceted approach, utilizing various prompt techniques, contributes to a comprehensive understanding of the subtle variations shaping misinformation sources.
{"title":"Silver Lining in the Fake News Cloud: Can Large Language Models Help Detect Misinformation?","authors":"Raghvendra Kumar;Bhargav Goddu;Sriparna Saha;Adam Jatowt","doi":"10.1109/TAI.2024.3440248","DOIUrl":"https://doi.org/10.1109/TAI.2024.3440248","url":null,"abstract":"In the times of advanced generative artificial intelligence, distinguishing truth from fallacy and deception has become a critical societal challenge. This research attempts to analyze the capabilities of large language models (LLMs) for detecting misinformation. Our study employs a versatile approach, covering multiple LLMs with few- and zero-shot prompting. These models are rigorously evaluated across various fake news and rumor detection datasets. Introducing a novel dimension, we additionally incorporate sentiment and emotion annotations to understand the emotional influence on misinformation detection using LLMs. Moreover, to extend our inquiry, we employ ChatGPT to intentionally distort authentic news as well as human-written fake news, utilizing zero-shot and iterative prompts. This deliberate corruption allows for a detailed examination of various parameters such as abstractness, concreteness, and named entity density, providing insights into differentiating between unaltered news, human-written fake news, and its LLM-corrupted counterpart. Our findings aspire to furnish a refined framework for discerning authentic news, human-generated misinformation, and LLM-induced distortions. This multifaceted approach, utilizing various prompt techniques, contributes to a comprehensive understanding of the subtle variations shaping misinformation sources.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 1","pages":"14-24"},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：