To reduce the time cost of training large scale parking data prediction model, this paper focuses on simplification of parking network topology from the graph coarsening perspective. First, merge ...adjacent parking lots into hypernodes via spectral distance to downscale the size of original parking network and form the coarsened graph while trying to keep the spatial characteristics of topology. Next, train an autoencoder to further compress the merged data of hypernode, getting a low-dimensional and denser representation which is more effective for spatiotemporal prediction. Then carry out prediction on the coarsened graph and obtain the results of hypernodes which are coarser than the intended predicted parking data. Finally decode the coarsened results via the pretrained autoencoder, restoring back to the original form of parking data to complete the whole task. The experimental results show that our proposed method improves the training efficiency by 1.61-2.73 times and reduces the error rate by 43.9%-51.5% on the real-world datasets compared to the traditional large scale parking data prediction methods.
In the era of big data, fragmented knowledge, multisource heterogeneity, and different representation forms of the same entities in various data sources have posed considerable challenges to entity ...fusion. How to effectively integrate multisource knowledge for the same entities has provoked vast amounts of attention and research from multiple disciplines. Most existing methods for entity fusion can be categorized into two classes: one is to establish an association between the same entities, and the other is to delete duplicate entities after knowledge fusion and create a new fusion entity. However, in these two classes of methods, the former does not achieve true knowledge fusion and semantic interoperability, while the latter may cause irreversible loss of original information. In this paper, we propose a novel entity fusion scheme: Hypernode. Hypernode fuses the same entity in different data sources into a new entity while retaining the original data. We verify the effectiveness of Hypernode on multiple models of link prediction experiments. Several practical application cases illustrate the applicability of Hypernode in data traceability, open domain knowledge fusion, and multi-modal knowledge graph fusion.
Graph neural networks (GNNs) are able to achieve state-of-the-art performance for node representation and classification in a network. But, most of the existing GNNs can be applied to simple graphs, ...where an edge connects only a pair of nodes. Studies have shown that hypergraphs are effective to model real-world relationships which are of higher order in nature. Recently, graph neural networks are proposed for hypergraphs, but they implicitly use clique or star expansions to convert the hypergraph to a simple graph, or use computationally expensive hypergraph Laplacian.In this work, we propose a novel hypergraph neural network for semi-supervised hypernode classification, which operates directly on the hypergraphs with varying hyperedge sizes. Within each layer, it indirectly works on the line graph of the given hypergraph, without actually forming the line graph explicitly. Moreover, it also employs a self-attention mechanism to learn the weights of those edge relationships. Experimentally, HAIN is able to improve the state-of-the-art hypernode classification performance on all the datasets we use. We make the source code available to ease the reproducibility of the results.
Currently, database researchers are investigating new data models in order to remedy the deficiencies of the flat relational model when applied to nonbusiness applications. Herein we concentrate on a ...recent graph based data model called the hypernode model. The single underlying data structure of this model is the hypernode which is a digraph with a unique defining label. We present in detail the three components of the model, namely its data structure, the hypernode, its query and update language, called HNQL, and its provision for enforcing integrity constraints. We first demonstrate that the said data model is a natural candidate for formalising hypertext. We then compare it with other graph based data models and with set based data models. We also investigate the expressive power of HNQL. Finally, using the hypernode model as a paradigm for graph based data modelling, we show how to bridge the gap between graph based and set based data models, and at what computational cost this can be done.< >
Hyperlog is a declarative, graph based language that supports database querying and update. It visualizes schema information, data, and query output as sets of nested graphs, which can be stored, ...browsed, and queried in a uniform way. Thus, the user need only be familiar with a very small set of syntactic constructs. Hyperlog queries consist of a set of graphs that are matched against the database. Database updates are supported by means of programs consisting of a set of rules. The paper discusses the formulation, evaluation, expressiveness, and optimization of Hyperlog queries and programs. We also describe a prototype implementation of the language and we compare and contrast our approach with work in a number of related areas, including visual database languages, graph based data models, database update languages, and production rule systems.