Table of Links Abstract and 1. Introduction Abstract and 1. Introduction Abstract and 1. Introduction Related Work


Preliminaries and Notations


Differentiable Structural Information
4.1. A New Formulation
4.2. Properties
4.3. Differentiability & Deep Graph Clustering


LSEnet
5.1. Embedding Leaf Nodes
5.2. Learning Parent Nodes
5.3. Hyperbolic Partitioning Tree


Experiments
6.1. Graph Clustering
6.2. Discussion on Structural Entropy


Conclusion, Broader Impact, and References Appendix Related Work Related Work Related Work Related Work Preliminaries and Notations Preliminaries and Notations Preliminaries and Notations Preliminaries and Notations Differentiable Structural Information
4.1. A New Formulation
4.2. Properties
4.3. Differentiability & Deep Graph Clustering Differentiable Structural Information Differentiable Structural Information Differentiable Structural Information 4.1. A New Formulation 4.1. A New Formulation 4.2. Properties 4.2. Properties 4.3. Differentiability & Deep Graph Clustering 4.3. Differentiability & Deep Graph Clustering LSEnet
5.1. Embedding Leaf Nodes
5.2. Learning Parent Nodes
5.3. Hyperbolic Partitioning Tree LSEnet LSEnet LSEnet 5.1. Embedding Leaf Nodes 5.1. Embedding Leaf Nodes 5.2. Learning Parent Nodes 5.2. Learning Parent Nodes 5.3. Hyperbolic Partitioning Tree 5.3. Hyperbolic Partitioning Tree Experiments
6.1. Graph Clustering
6.2. Discussion on Structural Entropy Experiments Experiments 6.1. Graph Clustering 6.1. Graph Clustering 6.2. Discussion on Structural Entropy 6.2. Discussion on Structural Entropy Conclusion, Broader Impact, and References Appendix Conclusion, Broader Impact, and References Appendix Conclusion, Broader Impact, and References Appendix Conclusion, Broader Impact, and References Appendix A. Proofs A. Proofs B. Hyperbolic Space B. Hyperbolic Space C. Technical Details C. Technical Details D. Additional Results D. Additional Results 5. LSEnet We propose a novel Lorentz Structural Entropy neural Net (LSEnet), which aims to learn the optimal partitioning tree T ∗ net in the Lorentz model of hyperbolic space, where we further incorporate node features with structural information by graph convolution net. First, we show the reason we opt for hyperbolic space, rather than Euclidean space. Hyperbolic space is well suited to embed the partitioning tree, and Theorem 5.1 does not hold for Euclidean space. Overall architecture of LSEnet is sketched in Figure 2. In hyperbolic space, LSEnet first embeds leaf nodes of the tree, and then recursively learns parent nodes, self-supervised by our new clustering objective Eq. (4). Overall architecture self-supervised by our new clustering objective Eq. Authors:
(1) Li Sun, North China Electric Power University, Beijing 102206, China (ccesunli@ncepu.edu);
(2) Zhenhao Huang, North China Electric Power University, Beijing 102206, China;
(3) Hao Peng, Beihang University, Beijing 100191, China;
(4) Yujie Wang, North China Electric Power University, Beijing 102206, China;
(5) Chunyang Liu, Didi Chuxing, Beijing, China;
(6) Philip S. Yu, University of Illinois at Chicago, IL, USA. Authors: Authors: (1) Li Sun, North China Electric Power University, Beijing 102206, China (ccesunli@ncepu.edu); (2) Zhenhao Huang, North China Electric Power University, Beijing 102206, China; (3) Hao Peng, Beihang University, Beijing 100191, China; (4) Yujie Wang, North China Electric Power University, Beijing 102206, China; (5) Chunyang Liu, Didi Chuxing, Beijing, China; (6) Philip S. Yu, University of Illinois at Chicago, IL, USA. This paper is available on arxiv under CC BY-NC-SA 4.0 Deed (Attribution-Noncommercial-Sharelike 4.0 International) license. This paper is available on arxiv under CC BY-NC-SA 4.0 Deed (Attribution-Noncommercial-Sharelike 4.0 International) license. available on arxiv available on arxiv

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

LSEnet: Mastering Automated Data Grouping in Curved Hyperbolic Space

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

A Comparative Performance Analysis of SymTax on Five Citation Recommendation Datasets

It Is Okay If You Don't Know What You Like. We Do (feat. Deep Recommendation Algorithms)

10 Machine Learning, Data Science, and Deep Learning Courses for Programmers in 2020

10 Computer Vision Startups on Product Hunt with the Most Upvotes

10 Best Entry Level Machine Learning Tutorials

10 Best + Free Machine Learning Courses Collection

A Comparative Performance Analysis of SymTax on Five Citation Recommendation Datasets

It Is Okay If You Don't Know What You Like. We Do (feat. Deep Recommendation Algorithms)

10 Machine Learning, Data Science, and Deep Learning Courses for Programmers in 2020

10 Computer Vision Startups on Product Hunt with the Most Upvotes

10 Best Entry Level Machine Learning Tutorials

10 Best + Free Machine Learning Courses Collection

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps