Abstract
Graph representation learning aims to learn a low-dimension latent representation of nodes, and the learned representation is used for downstream graph analysis tasks. However, most of the existing graph embedding models focus on how to aggregate all the neighborhood node features to encode the semantic information into the representation and neglect the global structural features of the node such as community structure and centrality. In the paper, we propose a novel unsupervised graph representation learning method (VHKRep), where a variable heat kernel is designed to better capture implicit global features via heat diffusion with the different time scale and generate the robust node representation. We conduct extensive experiment on three real-world datasets for node classification and link prediction tasks. Compared with the state-of-the-art seven models, the experimental results demonstrate the effectiveness of our proposed method on both node classification and link prediction tasks.
Highlights
graph as follows: Definition 1 (Graph) are a ubiquitous data structure, employed extensively within information networks and physical worlds [1]
We proposed a novel unsupervised graph representation learning approach, called VHKRep, which can capture more global structural features and more refined local structural features through heat kernel diffusion with different time scales
We propose a novel unsupervised graph embedding approach based on variable heat kernel, which can adequately capture refined structural information from local to global via different time scales
Summary
Graphs are a ubiquitous data structure, employed extensively within information networks (e.g., online social networks) and physical worlds (e.g., protein interaction networks) [1]. (3) Matrix factorization-based approaches model the high-order proximity of nodes to capture more global structures and obtain a low-dimensional representation of node by singular value decomposition (SVD) of relational matrix or similar matrix, such as Graph Factorization [12], Grarep [13] and Hope [14] These approaches based on matrix-factorization are inefficient when calculating the power of the adjacency matrix and decomposition of the relationship matrix in large-scale networks because of the data sparsity of the adjacency matrix. As shown in Fig., we give an illustrative example that shows the differences between the two strategies of exploring the graph structure By following this idea, we proposed a novel unsupervised graph representation learning approach, called VHKRep, which can capture more global structural features and more refined local structural features through heat kernel diffusion with different time scales. We propose a novel unsupervised graph embedding approach based on variable heat kernel, which can adequately capture refined structural information from local to global via different time scales.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
