An Unsupervised Learning Method for Attributed Network Based on Non-Euclidean Geometry
نویسندگان
چکیده
Many real-world networks can be modeled as attributed networks, where nodes are affiliated with attributes. When we implement network embedding, need to face two types of heterogeneous information, namely, structural information and attribute information. The undirected is usually expressed a symmetric adjacency matrix. Network embedding learning utilize the above learn vector representations in network. How integrate these improve performance challenge. Most current approaches embed Euclidean spaces, but themselves non-Euclidean. As consequence, geometric differences between embedded space underlying will affect embedding. According non-Euclidean geometry this paper proposes an framework based on hyperbolic Ricci curvature, RHAE. Our method consists modules: (1) first module autoencoder which each layer provided aggregation curvature geometry; (2) second skip-gram random walk curvature. These modules geometry, they fuse topology from different angles. Experimental results some benchmark datasets show that our approach outperforms baselines.
منابع مشابه
An Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network
RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...
متن کاملEuclidean Geometry before non-Euclidean Geometry
In [3], in my argument for the primacy of Euclidean geometry on the basis of rigid motions and the existence of similar but non-congruent triangles, I wrote the following: A: “The mobility of rigid objects is now recognized as one of the things every normal human child learns in infancy, and this learning appears to be part of our biological progaramming.” B. “. . . we are all used to thinking ...
متن کاملSpatial Analysis in curved spaces with Non-Euclidean Geometry
The ultimate goal of spatial information, both as part of technology and as science, is to answer questions and issues related to space, place, and location. Therefore, geometry is widely used for description, storage, and analysis. Undoubtedly, one of the most essential features of spatial information is geometric features, and one of the most obvious types of analysis is the geometric type an...
متن کاملA Nonlinear Grayscale Morphological and Unsupervised method for Human Facial Synthesis Based on an Example Image
Human facial generation of example image is used as a requirement for biometric applications for the purpose of identifying individuals. In this paper, face generation consists of three main steps. In the first step, detection of significant lines and edges of the example image are carried out using nonlinear grayscale morphology. Then, hair areas are identified from the face of sample. The fin...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Symmetry
سال: 2021
ISSN: ['0865-4824', '2226-1877']
DOI: https://doi.org/10.3390/sym13050905