HONEM: Learning Embedding for Higher Order Networks
Preprint
Abstract
Representation learning on networks offers a powerful alternative to the oft painstaking process of manual feature engineering, and as a result, has enjoyed considerable success in recent years. However, all the existing representation learning methods are based on the first-order network (FON), that is, the network that only captures the pairwise interactions between the nodes. As a result, these methods may fail to incorporate non-Markovian higher-order dependencies in the network. Thus, the embeddings that are generated may not accurately represent of the underlying phenomena in a network, resulting in inferior performance in different inductive or transductive learning tasks. To address this challenge, this paper presents HONEM, a higher-order network embedding method that captures the non-Markovian higher-order dependencies in a network. HONEM is specifically designed for the higher-order network structure (HON) and outperforms other state-of-the-art methods in node classification, network re-construction, link prediction, and visualization for networks that contain non-Markovian higher-order dependencies.Keywords
All Related Versions
- Version 1, 2019-08-15, ArXiv
- Version 2, 2020-09-03, ArXiv
- Published version: Big Data, 8 (4), 255.
This publication has 17 references indexed in Scilit:
- Graph embedding techniques, applications, and performance: A surveyKnowledge-Based Systems, 2018
- A Survey on Network EmbeddingIEEE Transactions on Knowledge and Data Engineering, 2018
- The physics of spreading processes in multilayer networksNature Physics, 2016
- Higher-order organization of complex networksScience, 2016
- Representing higher-order dependencies in networksScience Advances, 2016
- Causality-driven slow-down and speed-up of diffusion in non-Markovian temporal networksNature Communications, 2014
- Memory in network flows and its effects on spreading dynamics and community detectionNature Communications, 2014
- Motif-based communities in complex networksJournal of Physics A: Mathematical and Theoretical, 2008
- Nonlinear Dimensionality Reduction by Locally Linear EmbeddingScience, 2000
- The Approximation of One Matrix by Another of Lower RankPsychometrika, 1936