Date
2021-01-06Journal
Frontiers in Computational NeurosciencePublisher
Frontiers Media S.A.Type
Article
Metadata
Show full item recordAbstract
Functional microcircuits are useful for studying interactions among neural dynamics of neighboring neurons during cognition and emotion. A functional microcircuit is a group of neurons that are spatially close, and that exhibit synchronized neural activities. For computational analysis, functional microcircuits are represented by graphs, which pose special challenges when applied as input to machine learning algorithms. Graph embedding, which involves the conversion of graph data into low dimensional vector spaces, is a general method for addressing these challenges. In this paper, we discuss limitations of conventional graph embedding methods that make them ill-suited to the study of functional microcircuits. We then develop a novel graph embedding framework, called Weighted Graph Embedding with Vertex Identity Awareness (WGEVIA), that overcomes these limitations. Additionally, we introduce a dataset, called the five vertices dataset, that helps in assessing how well graph embedding methods are suited to functional microcircuit analysis. We demonstrate the utility of WGEVIA through extensive experiments involving real and simulated microcircuit data.Rights/Terms
Copyright © 2021 Wu, Bhattacharyya and Chen.Identifier to cite or link to this item
http://hdl.handle.net/10713/14705ae974a485f413a2113503eed53cd6c53
10.3389/fncom.2020.603765
Scopus Count
Collections
Related articles
- Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds.
- Authors: Grattarola D, Zambon D, Livi L, Alippi C
- Issue date: 2020 Jun
- Stochastic Graphlet Embedding.
- Authors: Dutta A, Sahbi H
- Issue date: 2019 Aug
- Learning a discriminant graph-based embedding with feature selection for image categorization.
- Authors: Zhu R, Dornaika F, Ruichek Y
- Issue date: 2019 Mar
- Decoding Time-Varying Functional Connectivity Networks via Linear Graph Embedding Methods.
- Authors: Monti RP, Lorenz R, Hellyer P, Leech R, Anagnostopoulos C, Montana G
- Issue date: 2017
- Hi-GCN: A hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction.
- Authors: Jiang H, Cao P, Xu M, Yang J, Zaiane O
- Issue date: 2020 Dec