Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs

Analysing Motifs in Multilayer Networks

Network motifs can capture basic interaction patterns and inform the functional properties of networks. However, real-world complex systems often have multiple types of relationships, which cannot be represented by a monolayer network. The multilayer nature of complex systems demands research on extending the notion of motifs to multilayer networks, thereby exploring the interaction patterns with a higher resolution. In this paper, we propose a formal definition of multilayer motifs, and analyse the occurrence of three-node multilayer motifs in a set of real-world multilayer networks. We find …

Motif-based Convolutional Neural Network on Graphs

This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to model the key properties of local connectivity and translation invariance, using high-order connection patterns or motifs. We develop a novel deep architecture Motif-CNN that employs an attention model to combine the features extracted from multiple patterns, thus effectively capturing high-order structural and feature information. Our experiments on semi-supe…

Higher-order Graph Convolutional Networks

Following the success of deep convolutional networks in various vision and speech related tasks, researchers have started investigating generalizations of the well-known technique for graph-structured data. A recently-proposed method called Graph Convolutional Networks has been able to achieve state-of-the-art results in the task of node classification. However, since the proposed method relies on localized first-order approximations of spectral graph convolutions, it is unable to capture higher-order interactions between nodes in the graph. In this work, we propose a motif-based graph attenti…

卷积神经网络用于基于遥感数据的蚀变填图矿产勘探

Convolutional neural networks for mineral prospecting through alteration mapping with remote sensing data

本研究利用CNN结合Landsat 8、Landsat 9和ASTER遥感数据，对澳大利亚布罗肯希尔北部蚀变带进行填图，通过地面真值训练和选择性PCA方法，证明CNN在捕捉空间模式上优于传统机器学习模型，并能有效识别细微矿化相关蚀变。

Isomorphisms in Multilayer Networks

We extend the concept of graph isomorphisms to multilayer networks with any number of "aspects" (i.e., types of layering). In developing this generalization, we identify multiple types of isomorphisms. For example, in multilayer networks with a single aspect, permuting vertex labels, layer labels, and both vertex labels and layer labels each yield different isomorphism relations between multilayer networks. Multilayer network isomorphisms lead naturally to defining isomorphisms in any of the numerous types of networks that can be represented as a multilayer network, and we thereby obtain isomo…

Multilayer network decoding versatility and trust

In the recent years, the multilayer networks have increasingly been realized as a more realistic framework to understand emergent physical phenomena in complex real world systems. We analyze a massive time-varying social data drawn from the largest film industry of the world under multilayer network framework. The framework enables us to evaluate the versatility of actors, which turns out to be an intrinsic property of lead actors. Versatility in dimers suggests that working with different types of nodes are more beneficial than with similar ones. However, the triangles yield a different relat…