This paper proposes a Metapath-Infused Exponential Decay graph neural network (MIED) approach for node embedding in heterogeneous graphs. It is designed to address limitations in existing methods, which usually lose the graph information during feature alignment and ignore the different importance of nodes during metapath aggregation. Firstly, graph convolutional network (GCN) is applied on the subgraphs, which is derived from the original graph with given metapaths to transform node features. Secondly, an exponential decay encoder (EDE) is designed, in which the influence of nodes on starting point decays exponentially with a fixed parameter as they move farther away from it. Thirdly, a set of experiments is conducted on two selected datasets of heterogeneous graphs, i.e., IMDb and DBLP, for comparison purposes. The results show that MIED outperforms selected approaches, e.g., GAT, HAN, MAGNN, etc. Thus, our approach is proven to be able to take full advantage of graph information considering node weights based on distance aspects. Finally, relevant parameters are analyzed and the recommended hyperparameter setting is given.
1 April 2021 in Journal of Physics: Conference Series
With the advent of the era of big data, extract and display effective information from massive amount of data has become a hot research field. Visualization is the most direct way for users to perceive and understand data. That’s why data dashboard with its cool dynamic visual effect has become so popular. In this paper, we propose a framework for rapid construction and development of web-based large screen visual dashboard—Anov. Anov dedicates to three goals: high efficiency, innovative AI user interaction and 3D scene. First, this framework provides a “30% configuration, 70% customization” development scheme which shortens the development cycle by at least one third. Second, Anov adopts a hierarchical architecture model to achieve high reusability, easy extensibility, high reliability, and easy maintenance. Finally, this paper introduces Anov’s wide range of application field and rich user experience through multiple cases to demonstrate the practicality of the framework.