A graph residual generation network for node classification based on multi-information aggregation

Graphs are a common and important data structure, and networks such as the Internet and social networks can be represented by graph structures. The proposal of Graph Convolutional Network (GCN) brings graph research into the era of deep learning and has achieved better results than traditional methods on various tasks. For ordinary neural networks, more layers can often achieve better results. However, for GCN, the deepening of the number of layers will cause a catastrophic decline in performance, including the gradual indistinguishability of node features, the disappearance of gradients, and the inability to update weights. This phenomenon is called over-smoothing. The occurrence of over-smoothing makes training deep GCNs a difficult problem. Compared with deep GCNs, shallow GCNs tend to perform better. Therefore, we design a contrastive learning model such that the deep GCN learns the features of the same node (positive samples) of the shallow GCN while alienating the features of other nodes (negative samples) , so that the deep GCN can learn the performance of the shallow GCN. Experiments show that our method can effectively alleviate the over-smoothing phenomenon. At the same time, we apply this model to other over-smoothing methods, and also achieve better results.KeywordsGraph convolutional networkGraph contrastive learningOver-smoothing

Recently, recommendation algorithms based on Graph Convolution Network (GCN) have achieved many surprising results thanks to the ability of GCN to learn more efficient node embeddings. However, although GCN shows powerful feature extraction capability in user-item bipartite graphs, the GCN-based methods appear powerless for knowledge graph (KG) with complex structures and rich information. In addition, all of the existing GCN-based recommendation systems suffer from the over-smoothing problem, which results in the models not being able to utilize higher-order neighborhood information, and thus these models always achieve their best performance at shallower layers. In this paper, we propose a Deep Light Graph Convolution Network for Knowledge Graph (KDL-GCN) to alleviate the above limitations. Firstly, the User-Entity Bipartite Graph approach (UE-BP) is proposed to simplify knowledge graph, which leverages entity information by constructing multiple interaction graphs. Secondly, a Deep Light Graph Convolution Network (DLGCN) is designed to make full use of higher-order neighborhood information. Finally, experiments on three real-world datasets show that the KDL-GCN proposed in this paper achieves substantial improvement compared to the state-of-the-art methods.

Exploiting node-feature bipartite graph in graph convolutional networks

Graph convolutional networks (GCNs) have achieved impressive success in many graph related analytics tasks. However, most GCNs only work in a single domain (graph) incapable of transferring knowledge from/to other domains (graphs), due to the challenges in both graph representation learning and domain adaptation over graph structures. In this paper, we present a novel approach, unsupervised domain adaptive graph convolutional networks (UDA-GCN), for domain adaptation learning for graphs. To enable effective graph representation learning, we first develop a dual graph convolutional network component, which jointly exploits local and global consistency for feature aggregation. An attention mechanism is further used to produce a unified representation for each node in different graphs. To facilitate knowledge transfer between graphs, we propose a domain adaptive learning module to optimize three different loss functions, namely source classifier loss, domain classifier loss, and target classifier loss as a whole, thus our model can differentiate class labels in the source domain, samples from different domains, the class labels from the target domain, respectively. Experimental results on real-world datasets in the node classification task validate the performance of our method, compared to state-of-the-art graph neural network algorithms.

Aiming at the problems of diversification, complexity and islanding of power operation and inspection data and the high dependence of operation and inspection operations on expert experience and normative information, the key technology research of intelligent judgment of defect types of power operation inspection equipment is carried out. For the field of power operation and inspection, the defect text classification algorithm based on graph convolutional neural network is proposed. And the practical tests in a large defect text network diagram built by main transformer defect reports are performed. And the proposed model achieves better classification results than 7 benchmark models in the defect text classification task. Specifically, the Accuracy, Weighed-Precision, and Weighed-F1 indicators reach 73.39, 72.42, and 72.21 respectively, which improves the model’s ability to identify defect types to a greater extent and plays an important role in improving the intelligence and digitalization of power operation and inspection work.

Recently, graph convolutional network (GCN) has drawn increasing attention in hyperspectral image (HSI) classification, as it can process arbitrary non-Euclidean data. However, dynamic GCN that refines the graph heavily relies on the graph embedding in the previous layer, which will result in performance degradation when the embedding contains noise. In this letter, we propose a novel dual residual graph convolutional network (DRGCN) for HSI classification that integrates two adjacency matrices of dual GCN. In detail, one GCN applies a soft adjacency matrix to extract spatial features, the other utilizes the dynamic adjacency matrix to extract global context-aware features. Subsequently, the features extracted by dual GCN are fused to make full use of the complementary and correlated information among two graph representations. Moreover, we introduce residual learning to optimize graph convolutional layers during the training process, to alleviate the over-smoothing problem. The advantage of dual GCN is that it can extract robust and discriminative features from HSI. Extensive experiments on four HSI data sets, including Indian Pines, Pavia University, Salinas, and Houston University, demonstrate the effectiveness and superiority of our proposed DRGCN, even with small-sized training data.

With the continuous development of landscape restoration technology, how to use modern technology to efficiently reconstruct degraded and damaged historical gardens to help them restore and protect has become an important topic. Traditional 3D reconstruction methods often face challenges in accuracy and efficiency when facing complex garden geometry and ecological environment. To this end, this paper proposes a hybrid model DGA-Net that combines deep convolutional network (DCN), graph convolutional network (GCN) and attention mechanism to improve the 3D reconstruction accuracy and detail recovery in historical garden landscape restoration. DGA-Net extracts spatial features through DCN, uses GCN to model the topological relationship of point clouds, and optimizes the recovery of key geometric details by combining attention mechanism. Compared with traditional methods, this hybrid method shows better performance in the reconstruction of complex structures and ecological characteristics of historical gardens, especially in the accuracy of point cloud generation and detail recovery. Experimental results show that DGA-Net can reconstruct the structure and ecological characteristics of historical gardens more finely, providing higher reconstruction accuracy and efficiency. This study provides innovative technical support for digital modeling and monitoring in landscape restoration, especially in the fields of ecological environment restoration and cultural heritage protection.

Label Distribution Learning (LDL), as a more general learning setting than generic single-label and multi-label learning, has been commonly used in computer vision and many other applications. To date, existing LDL approaches are designed and applied to data without considering the interdependence between instances. In this paper, we propose a Graph Label Distribution Learning (GLDL) framework, which explicitly models three types of relationships: instance-instance, label-label, and instance-label, to learn the label distribution for networked data. A label-label network is learned to capture label-to-label correlation, through which GLDL can accurately learn label distributions for nodes. Dual graph convolution network (GCN) Co-training with heterogeneous message passing ensures two GCNs, one focusing on instance-instance relationship and the other one targeting label-label correlation, are jointly trained such that instance-instance relationship can help induce label-label correlation and vice versa. Our theoretical study derives the error bound of GLDL. For verification, four benchmark datasets with label distributions for nodes are created using common graph benchmarks. The experiments show that considering dependency helps learn better label distributions for networked data, compared to state-of-the-art LDL baseline. In addition, GLDL not only outperforms simple GCN and graph attention networks (GAT) using distribution loss but is also superior to its variant considering label-label relationship as a static network. GLDL and its benchmarks are the first research endeavors to address LDL for graphs. Code and benchmark data are released for public access.

A multi-scale semantic attention representation for multi-label image recognition with graph networks

LightGCAN: A lightweight graph convolutional attention network for user preference modeling and personalized recommendation

Cross-subject emotion recognition in brain-computer interface based on frequency band attention graph convolutional adversarial neural networks

Graph Convolutional Network (GCN) is an emerging technique that performs learning and reasoning on graph data. It operates feature learning on the graph structure, through aggregating the features of the neighbor nodes to obtain the embedding of each target node. Owing to the strong representation power, recent research shows that GCN achieves state-of-the-art performance on several tasks such as recommendation and linked document classification. Despite its effectiveness, we argue that existing designs of GCN forgo modeling cross features, making GCN less effective for tasks or data where cross features are important. Although neural network can approximate any continuous function, including the multiplication operator for modeling feature crosses, it can be rather inefficient to do so (i.e., wasting many parameters at the risk of overfitting) if there is no explicit design. To this end, we design a new operator named Cross-feature Graph Convolution, which explicitly models the arbitrary-order cross features with complexity linear to feature dimension and order size. We term our proposed architecture as Cross-GCN, and conduct experiments on three graphs to validate its effectiveness. Extensive analysis validates the utility of explicitly modeling cross features in GCN, especially for feature learning at lower layers.

Graph convolutional network (GCN) based approaches have achieved significant progress for solving complex, graph-structured problems. GCNs incorporate the graph structure information and the node (or edge) features through message passing and computes ‘deep’ node representations. Despite significant progress in the field, designing GCN architectures for heterogeneous graphs still remains an open challenge. Due to the schema of a heterogeneous graph, useful information may reside multiple hops away. A key question is how to perform message passing to incorporate information of neighbors multiple hops away while avoiding the well-known over-smoothing problem in GCNs. To address this question, we propose our GCN framework Deep Heterogeneous Graph Convolutional Network (DHGCN), which takes advantage of the schema of a heterogeneous graph and uses a hierarchical approach to effectively utilize information many hops away. It first computes representations of the target nodes based on their schema-derived ego-network (SEN). It then links the nodes of the same type with various pre-defined metapaths and performs message passing along these links to compute final node representations. Our design choices naturally capture the way a heterogeneous graph is generated from the schema. The experimental results on real and synthetic datasets corroborate the design choice and illustrate the performance gains relative to competing alternatives.

Entity linking, which maps named entity mentions in a document into the proper entities in a given knowledge graph, has been shown to be able to significantly benefit from modeling the entity relatedness through Graph Convolutional Networks (GCN). Nevertheless, existing GCN entity linking models fail to take into account the fact that the structured graph for a set of entities not only depends on the contextual information of the given document but also adaptively changes on different aggregation layers of the GCN, resulting in insufficiency in terms of capturing the structural information among entities. In this paper, we propose a dynamic GCN architecture to effectively cope with this challenge. The graph structure in our model is dynamically computed and modified during training. Through aggregating knowledge from dynamically linked nodes, our GCN model can collectively identify the entity mappings between the document and the knowledge graph, and efficiently capture the topical coherence among various entity mentions in the entire document. Empirical studies on benchmark entity linking data sets confirm the superior performance of our proposed strategy and the benefits of the dynamic graph structure.

The objective of extracting relations between document components lies in identifying the Within a single document, the focus often lies on understanding the connections between different entities. This type of analysis goes beyond individual sentences, as it demands an understanding of how information from multiple sentences interacts to form these connections. Over recent years, the importance of exploring relationships involving several entities simultaneously has grown significantly. To advance the field of studying such connections across entire documents, a novel collection of data points, known as DocRED, has been introduced. Currently, the standard approach for this task involves using BiLSTM networks to process the entire document as a whole. However, this method struggles to effectively capture the intricate relationships that exist among various entities. To overcome this limitation, a new model designed for document-level relationship identification has been developed, which leverages Graph Convolutional Networks (GCN). GCNs are particularly useful here because they can gather information from surrounding entities, allowing for a more detailed modeling of their interactions. The proposed approach starts by identifying coreferential links to gather features that represent the relationships between pairs of entities. These features are then analyzed using GCN to construct a graph structure that represents the entire document, ultimately revealing the complex interactions between different entities. Testing this model on the large-scale DocRED dataset from Tsinghua University has demonstrated its strong performance in this challenging task.