Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Wang Li et al.
Summary: This paper proposes a novel deep attributed graph clustering network with a multi-level subspace fusion module to address the challenge of choosing the proper neighborhood for attributed graph clustering. The network inserts multiple self-expressive modules between low-level and high-level layers to promote more favorable features for clustering. With the constraint of shared self-expressive matrix, the intrinsic structure is preserved without pre-defined neighborhoods. Furthermore, a novel loss function is introduced to effectively preserve multi-level clustering structures with both global and local discriminative features.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Jinfu Fan et al.
Summary: This paper proposes an innovative approach called GraphDPI for deep partial label disambiguation by graph representation and mutual information maximization. The experiments demonstrate the outstanding performance of this method.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Information Systems
Zongqian Wu et al.
Summary: In this paper, a Multi-Task and Multi-Graph Convolutional Network (MTGCN) is proposed to conduct node classification and link prediction simultaneously. MTGCN consists of multiple multi-task learning to capture the complementary information between node classification and link prediction, and enhances the information to guarantee the quality of representations by exploring the complex structure inherent in the graph data.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Artificial Intelligence
Xue Liu et al.
Summary: This paper introduces a novel graph entropy definition to evaluate the smoothness of a data manifold and proposes a strategy to generate randomly perturbed training data while preserving both graph topology and graph entropy. Experimental results demonstrate the effectiveness of the method in improving semi-supervised node classification accuracy and enhancing the robustness of the training process for GCN.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Shilei Wang et al.
Summary: Online recommender systems are prone to group shilling attacks, where attackers collaborate to inject fake profiles to manipulate recommendations. Existing detection methods suffer from the limitations of generating candidate groups and relying on manual feature engineering. To overcome these limitations, a shilling group detection method based on graph convolutional network is proposed, which achieves high accuracy and performance on Netflix and Amazon datasets.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Artificial Intelligence
Wenfeng Zheng et al.
Summary: This paper constructs a knowledge base graph embedding module to extend the versatility of knowledge-based VQA models. By extracting core entities from images and text and performing sub-graph embedding, the accuracy of knowledge-based VQA models is improved.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Yansong Gong et al.
Summary: This study proposes a two-level framework for 3D LiDAR place recognition based on spatial relation graphs (SRGs), which includes point cloud segmentation, feature and spatial relation descriptor extraction, and accurate and efficient matching of SRGs through a two-level matching model. Experimental results demonstrate the good performance of the framework in place recognition.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Chunrong Wu et al.
Summary: Hierarchical clustering method HCNN effectively groups similar data by utilizing structural similarities in the nearest neighbor graph, identifying clusters and outliers while reducing the influence of obscure boundaries. The method merges clusters more efficiently by considering equivalence relations based on maximum similarity, leading to improved clustering efficiency and accuracy.
KNOWLEDGE-BASED SYSTEMS
(2021)
Proceedings Paper
Computer Science, Information Systems
Jun Wu et al.
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING
(2019)
