Search

Exploring relationships in complex datasets is one of the challenges in today's big data era. The graph-based visualization approach, which integrates the advantages of graph analysis theory and visualization technologies and combines machine and human intelligence, has become an effective means for analyzing various relationships in complex datasets. In this paper, we first introduce a graph-based visual analytics model for associated data. Then, we summarize seven typical visualization methods for associated data according to their layout features, including their node-link diagram, adjacency matrix, hypergraph, flow diagram, graphs with geospatial information, multi-attribute graph, and space-filling diagram and discuss their advantages and disadvantages. We describe current graph simplification and interaction techniques, including graph filtering, node clustering, edge bundling, graph data dimension reduction, and topology-based graph transformation. Finally, we discuss the potential challenges and developmental trends of the research direction. [ABSTRACT FROM AUTHOR]

Graph embedding, which constructs vector representation of nodes in a network, has shown effectiveness in many graph analysis tasks, such as node classification, node clustering, and link prediction. However, due to the complexity of graph embedding models (GEMs) and their nontransparency of hyperparameters, evaluation and comparison of embedding results in retaining the original graph features, and consequently, the selection of suitable GEMs according to graph analysis tasks are challenging for people. In this paper, we present a visual analysis method, GEMvis, to support the evaluation and comparison of GEMs from the original graph, node metric, and embedding result spaces. The method also supports the online refining of GEM by tuning the parameters in its three components (graph sampling method, neural network structure, and loss function). A series of metrics, R_node metrics, for measuring GEMs' ability to preserve specific node metrics, such as R_degree and R_closeness, is also proposed to support quantitative evaluation and comparison of GEMs' ability to preserve original graph features. Finally, three case studies and expert feedback illustrate the effectiveness of GEMvis. [ABSTRACT FROM AUTHOR]

Computer science discipline includes many research fields, which mutually influence and promote each other's development. This poses two great challenges of predicting the research topics of each research field. One is how to model fine-grained topic representation of a research field. The other is how to model research topic of different fields and keep the semantic consistency of research topics when learning the scientific influence context from other related fields. Unfortunately, the existing research topic prediction approaches cannot handle these two challenges. To solve these problems, we employ multiple different Recurrent Neural Network chains which model research topics of different fields and propose a research topic prediction model based on spatial attention and semantic consistency-based scientific influence modeling. Spatial attention is employed in field topic representation which can selectively extract the attributes from the field topics to distinguish the importance of field topic attributes. Semantic consistency-based scientific influence modeling maps research topics of different fields to a unified semantic space to obtain the scientific influence context of other related fields. Extensive experiment results on five related research fields in the computer science (CS) discipline show that the proposed model is superior to the most advanced methods and achieves good topic prediction performance. [ABSTRACT FROM AUTHOR]

Unsupervised graph learning aims to learn an encoder that embeds high-dimensional nodes into compact continuous vectors and preserves the topological and semantic features simultaneously without using any label information. Recently, contrastive learning (CL) on graph learning revives the traditional InfoMax principle and generates two views of the input graph randomly and then maximizes the agreements between them. However, the stochastic augmentation of a graph leads to two problems that need to be solved. Firstly, it ignores the role of some essential nodes and discriminating feature dimensions on the graph and may decrease the informativeness of the generated view by removing these crucial edges. Secondly, there are multi-level substructures of a graph that can be exploited and utilized for the network encoder's topological learning. This paper proposes Cluster-Aware Multiplex InfoMax (CAMI) for unsupervised graph representation learning. We apply an adaptive graph augmentation scheme on both topological and feature dimensions to generate graph views without damaging the vital graph structure. To encourage the network encoder to capture more underlying node interactions, we additionally increase a mutual information maximization constraint between the node's representation and multi-level graph summaries. Extensive experimental results on seven realistic datasets with different tasks prove the CAMI framework's effectiveness. [ABSTRACT FROM AUTHOR]

The problem of global warming is getting more serious, and vehicle emission is the main cause. In recent years, the number of locomotives in China has been increasing at a rate of more than 20% per year, and the problem of automobile pollution is becoming more serious. The transportation industry is the main source of fossil fuel combustion and environmental pollution. Therefore, in this paper, we propose a multi-view deep neural network (MVDNN) to analyze the key factors affecting the fuel consumption of automobiles. The experiments show that the introduction of human input improves the prediction accuracy and the root mean square error (RMSE) achieves 0.993. In addition, this paper also finds that for drivers, driving habits, driving frequency, and safety awareness are the most important factors affecting the fuel consumption of vehicles by combining Lasso regression with MVDNN. Finally, by comparing the prediction accuracy of different experiments, relevant policy suggestions are made. [ABSTRACT FROM AUTHOR]