Hyperparameter-free and Explainable Whole Graph Embedding

Abstract

Graphs can be used to describe complex systems. Recently, whole graph embedding (graph representation learning) can compress a graph into a compact lower-dimension vector while preserving intrinsic properties, earning much attention. However, most graph embedding methods have problems such as tedious parameter tuning or poor explanation. This paper presents a simple and hyperparameter-free whole graph embedding method based on the DHC (Degree, H-index, and Coreness) theorem and Shannon Entropy (E), abbreviated as DHC-E. The DHC-E can provide a trade-off between simplicity and quality for supervised classification learning tasks involving molecular, social, and brain networks. Moreover, it performs well in lower-dimensional graph visualization. Overall, the DHC-E is simple, hyperparameter-free, and explainable for whole graph embedding with promising potential for exploring graph classification and lower-dimensional graph visualization.

References in corpus (12)

• Efficient Estimation of Word Representations in Vector Space
• An index to quantify an individual's scientific research output
• The diameter of the world wide web
• Identification of influential spreaders in complex networks
• k-core organization of complex networks
• graph2vec: Learning Distributed Representations of Graphs
• A Survey on Graph Kernels
• Learning Graph Embedding with Adversarial Training Methods
• TUDataset: A collection of benchmark datasets for learning with graphs
• Spreading dynamics in complex networks
• NetLSD: Hearing the Shape of a Graph
• Deep Network Embedding for Graph Representation Learning in Signed Networks

Cited by in corpus (2)

• Recommender systems based on graph embedding techniques: A comprehensive review
• Determinable and interpretable network representation for link prediction