Article
Computer Science, Information Systems
Na Hu, Dafang Zhang, Kun Xie, Wei Liang, Kuanching Li, Albert Zomaya
Summary: Traffic prediction is crucial for transportation management and travel route planning. This study proposes a multi-Graph Fusion-based Graph Convolutional Network (GFGCN) that can effectively capture complex spatial dependencies and dynamic temporal patterns.
COMPUTER COMMUNICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Zhihao Wang, Ding Ding, Xia Liang
Summary: This paper studies the problem of traffic forecasting and proposes a novel Traffic dYnamic gRaph modEl (TYRE) that captures temporal and spatial dependencies. The model improves long-term traffic prediction significantly and outperforms previous approaches.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
Renyi Chen, Huaxiong Yao
Summary: This paper proposes a Hybrid Graph Model (HGM) for accurate traffic prediction, which constructs a static graph and a dynamic graph to represent the topological information of the traffic network and extract complex spatial-temporal features. The HGM combines graph neural network, convolutional neural network, and attention mechanism to improve prediction performance. Extensive experiments show that the HGM outperforms comparable state-of-the-art methods.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Xu Huang, Bowen Zhang, Shanshan Feng, Yunming Ye, Xutao Li
Summary: In this paper, an interpretable local flow attention (LFA) mechanism is proposed for traffic flow prediction (TFP), which has the advantages of flow-awareness, interpretability, and efficiency. Based on LFA, a novel spatiotemporal cell called LFA-ConvLSTM is developed to capture the complex dynamics in traffic data. Experimental results demonstrate that our method outperforms previous approaches in prediction performance and is also faster by 32% than global self-attention ConvLSTM.
Article
Computer Science, Hardware & Architecture
Zilong Jin, Jun Qian, Zhixiang Kong, Chengsheng Pan
Summary: This paper proposes an efficient network traffic prediction model that utilizes spatio-temporal graph attention to capture correlations among node traffic sequences and fuse spatio-temporal features. Experimental results demonstrate that the proposed method outperforms existing methods in terms of performance and long-term prediction capability.
Article
Computer Science, Artificial Intelligence
Youfa Liu, Shufan Tong, Yongyong Chen
Summary: This paper proposes a new architecture of GNNs for drug response prediction in cancer, utilizing multi-omics data and STRING protein-protein association data to construct a multi-view graph. The proposed HMM-GDAN model demonstrates superior performance compared to previous baselines, highlighting the effectiveness of multi-view and multi-scale strategies.
Article
Transportation
Chuang Ma, Li Yan, Guangxia Xu
Summary: This paper proposes a traffic flow prediction model, the Spatio-Temporal Graph Attention Network (STGAN), which utilizes graph attention mechanisms and gated recurrent units to effectively capture the spatial and temporal features of traffic flow.
TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Jie Su, Zhongfu Jin, Jie Ren, Jiandang Yang, Yong Liu
Summary: In this paper, a novel traffic flow prediction approach called GDFormer is proposed, which adopts the architecture of transformer and utilizes the GDA module to learn diffusion parameters and dynamically update adjacency transition. The approach achieves state-of-the-art performance through extensive experiments on two real-world datasets, and the effectiveness of the model is demonstrated through ablative experiments.
PATTERN RECOGNITION LETTERS
(2022)
Article
Engineering, Civil
Duo Li, Joan Lasenby
Summary: The study introduces an attention-based spatiotemporal graph attention network (AST-GAT) for segment-level traffic speed prediction, which outperforms existing models by capturing spatial dependencies, integrating speed, volume, and weather information, and using attention-based LSTM for temporal learning and speed prediction on road segments.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Chengcheng Sun, Chenhao Li, Xiang Lin, Tianji Zheng, Fanrong Meng, Xiaobin Rui, Zhixiao Wang
Summary: This paper provides a comprehensive survey on recent advances in attention-based graph neural networks (GNNs). It proposes a two-level taxonomy for attention-based GNNs and reviews these methods in detail, summarizing their advantages and disadvantages. The paper also discusses open issues and future directions for attention-based GNNs.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Engineering, Civil
Xiaoming Shi, Heng Qi, Yanming Shen, Genze Wu, Baocai Yin
Summary: Accurate traffic forecasting is important in smart cities, and the proposed APTN model effectively captures spatial, short-term, and long-term dependencies using attention mechanisms. The model shows consistent improvements over state-of-the-art baselines when evaluated with real world traffic datasets.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Information Systems
Peixiao Wang, Yan Zhang, Tao Hu, Tong Zhang
Summary: This study proposes a dynamic temporal graph neural network model that considers missing values and dynamic spatial relationships for urban traffic flow prediction. The model achieves good prediction results and outperforms existing baselines on a real traffic dataset.
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
(2023)
Article
Computer Science, Information Systems
Junzhong Ji, Yating Ren, Minglong Lei
Summary: This study proposes a hypergraph attention network (FC-HAT) for functional brain network classification, which dynamically generates hypergraphs and extracts high-order information using attention mechanisms. Experimental results demonstrate the effectiveness of FC-HAT in cerebral disease classification and the identification of biomarkers associated with cerebral diseases.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Zhilong Lu, Weifeng Lv, Zhipu Xie, Bowen Du, Guixi Xiong, Leilei Sun, Haiquan Wang
Summary: In this article, a Graph Sequence neural network with an Attention mechanism (GSeqAtt) is proposed to handle information propagation for graph sequences. The model combines horizontal and vertical attention mechanisms to capture the correlations between graphs in the input time sequence and within the graph structure in each frame of the time series. Experimental results show that GSeqAtt outperforms state-of-the-art baselines on the traffic speed prediction task.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2022)
Article
Chemistry, Analytical
Jianrun Shi, Leiyang Cui, Bo Gu, Bin Lyu, Shimin Gong
Summary: This paper proposes a state transition graph-based spatial-temporal attention network (STG-STAN) for cell-level mobile traffic prediction, which can better exploit the spatial-temporal information hidden in the historical data.
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.