Article
Computer Science, Artificial Intelligence
Xiaoyu Xu, Xiaoyu Shi, Mingsheng Shang
Summary: This research introduces a novel approach for effectively learning node representations in disassortative graph structures. The proposed method synthesizes the feature semantic space and the structure semantic space to find friendly neighbor spaces and learns the interrelationship between aggregated information and separated information using contrastive learning. Experimental results show that the proposed approach outperforms eight state-of-the-art GNN models in various graph mining tasks, demonstrating its superior graph representation ability.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Mathematics
Xinglong Chang, Jianrong Wang, Rui Guo, Yingkui Wang, Weihao Li
Summary: This paper proposes a simple method to solve the problem of collapsing solutions in unsupervised graph representation learning. By using contrastive learning and an asymmetric design, the method achieves effective graph representation learning.
Article
Mathematics
Wenchuan Zhang, Weihua Ou, Weian Li, Jianping Gou, Wenjun Xiao, Bin Liu
Summary: Graph neural networks (GNNs) have gained attention for effectively processing graph-related data. Existing methods assume noise-free input graphs, which is frequently violated in real-world scenarios. To address this issue, we introduce virtual nodes and utilize Gumbel-Softmax to reweight edges, achieving differentiable graph structure learning (abbreviated as VN-GSL). Thorough evaluations on benchmark datasets demonstrate the superiority of our approach in terms of performance and efficiency. Our implementation will be publicly available.
Article
Computer Science, Artificial Intelligence
Jianian Zhu, Weixin Zeng, Junfeng Zhang, Jiuyang Tang, Xiang Zhao
Summary: Graph contrastive learning (GCL) offers a new perspective to reduce the reliance on labeled data for graph representation learning. Existing GCL methods utilize graph augmentation strategies such as node dropping and edge masking, to create augmented views of the original graph for contrastive learning. However, these methods are limited in capturing sufficient information for contrastive learning. This work proposes the use of hypergraph to establish a new view for graph contrastive learning, enabling the capture of high-order information and improving the quality of graph representations through the contrast between the hypergraph view and the original graph view.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Li Zhang, Heda Song, Nikolaos Aletras, Haiping Lu
Summary: Graph convolutional network (GCN) is an effective neural network model for graph representation learning. This paper proposes a new node-feature convolutional (NFC) layer to tackle the limitations of standard GCN. Experimental results show that NFC-GCN outperforms state-of-the-art methods in node classification.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Zhenfei Luo, Yixiang Dong, Qinghua Zheng, Huan Liu, Minnan Luo
Summary: Self-supervised graph-level representation learning aims to learn discriminative representations for sub-graphs or entire graphs without human-curated labels. The proposed DualGCL framework utilizes an adaptive hierarchical aggregation process and a dual-channel contrastive learning process to achieve better performance in graph classification benchmarks.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Weimin Li, Lin Ni, Jianjia Wang, Can Wang
Summary: This paper proposes a new heterogeneous graph neural network model called CoNR for link prediction task. The model learns node representations and relation representations collaboratively to improve the performance of downstream tasks.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Wei Ju, Yiyang Gu, Xiao Luo, Yifan Wang, Haochen Yuan, Huasong Zhong, Ming Zhang
Summary: This paper proposes an unsupervised graph-level representation learning framework called Hierarchical Graph Contrastive Learning (HGCL), which addresses the issues of limited exploration of semantic information for graph representation and memory problems during optimization in graph domains. HGCL investigates the hierarchical structural semantics of a graph at both node and graph levels through contrastive learning. Experimental results demonstrate that HGCL outperforms a broad range of state-of-the-art baselines in graph classification and transfer learning tasks.
Article
Computer Science, Artificial Intelligence
Joshua Melton, Siddharth Krishnan
Summary: This paper proposes muxGNN, a multiplex graph neural network for heterogeneous graphs. It models heterogeneity by representing graphs as multiplex networks consisting of relation layer graphs and a coupling graph. Parameterizing relation-specific representations of nodes and designing a novel coupling attention mechanism, muxGNN captures the importance of multi-relational contexts in heterogeneous graphs. Experimental results on real-world datasets demonstrate the superior performance of muxGNN in link prediction and graph classification tasks compared to state-of-the-art heterogeneous GNNs. Additionally, muxGNN's coupling attention discovers interpretable connections between different relations in heterogeneous networks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yuanyuan Liu, Zhaoqian Zhong, Chao Che, Yongjun Zhu
Summary: This study proposes a model called Knowledge Graph Residual Negative Sampling Recommendation (KGRNS) to address the problem of over-smoothing in collaborative filtering. The model utilizes residual connections and pooling operation to mitigate the over-smoothing problem, and generates high-quality negative samples through negative sampling. Experimental results show that KGRNS achieves significant improvements in the recommendation system.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Information Systems
Quanmin Wei, Jinyan Wang, Xingcheng Fu, Jun Hu, Xianxian Li
Summary: This paper proposes a pluggable framework called Adversarial Information Completion Graph Neural Networks (AIC-GNN) to address the problem of low-degree node representation learning. A novel Graph Information Generator is introduced to adaptively fit the node missing information distribution, and adversarial training is used to enhance the representational capacity of the model. Extensive experiments demonstrate the superior performance of AIC-GNN compared to state-of-the-art methods on four real-world graphs.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Meixin Peng, Xin Juan, Zhanshan Li
Summary: In this paper, we propose a Graph Prototypical Contrastive Learning (GPCL) framework for unsupervised graph representation learning. The GPCL framework not only models instance-level feature similarity but also explores the underlying semantic structure of the whole data. By introducing instance-prototype contrastive objective and prototype-prototype contrastive objective, the GPCL method can learn representations that are discriminative to inter-class variance and invariant to intra-class variance.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Xiaoyu Xu, Guansong Pang, Di Wu, Mingsheng Shang
Summary: This paper proposes a novel graph neural network model called JointGMC, which learns representations in both Euclidean and hyperbolic spaces to effectively encode complex graph structures. The model exploits self-supervised information to regularize graph learning and does not rely heavily on manually labeled data. Experimental results demonstrate that JointGMC outperforms eight state-of-the-art GNN models in multiple graph mining tasks.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Bo Jiang, Beibei Wang, Si Chen, Jin Tang, Bin Luo
Summary: This article proposes a Graph Sparse Neural Networks (GSNNs) model based on the theory of sparse representation, which conducts sparse aggregation to select reliable neighbors for message propagation. Furthermore, it introduces Exclusive Group Lasso GNNs (EGLassoGNNs) as a tight continuous relaxation model for optimizing GSNNs. Experimental results demonstrate the superior performance and robustness of the proposed EGLassoGNNs model.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Zhaowei Liu, Dong Yang, Yingjie Wang, Mingjie Lu, Ranran Li
Summary: In recent years, graph neural networks (GNNs) have achieved state-of-the-art performance in various fields due to their characteristics of neighborhood aggregation. However, the performance of GNNs is often suboptimal due to noisy or incomplete original graph data. To address this problem, a new Graph Structure Learning (GSL) method called evolutionary graph neural network (EGNN) has been introduced in this work. Unlike existing GSL methods, EGNN applies evolutionary theory to graph structure learning, using mutation operations to generate different graph structures and evolving a set of model parameters that adapt to the environment. Through an evaluation mechanism, only the progeny with good performance are retained for further optimization. Extensive experiments demonstrate the effectiveness of EGNN and the benefits of evolutionary computation-based graph structure learning.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.