无超参数可解释的全图嵌入
Hyperparameter-free and Explainable Whole Graph Embedding
摘要：
图形可以用来描述复杂的系统。近年来，全图嵌入（图表示学习）能够在保持图的固有性质的同时将图压缩成一个紧凑的低维向量，引起了人们的广泛关注。然而，大多数图嵌入方法都存在参数调整繁琐或解释性差等问题。基于DHC（Degree，H-index，and Coreness）定理和香农熵（Shannon Entropy，E），提出了一种简单的无超参数的全图嵌入方法，简称DHC-E。DHC-E可以为涉及分子，社会和大脑网络的监督分类学习任务提供简单性和质量之间的权衡。此外，它在低维图形可视化方面表现良好。总的来说，DHC-E是简单的，无超参数的，并且可以解释整个图嵌入，具有探索图分类和低维图可视化的潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
