Link Prediction Schemes Contra Weisfeiler-Leman Models
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2018, Vol 9, Issue 6
Abstract
Link prediction is of particular interest to the data mining and machine learning communities. Until recently all approaches to the problem used embedding-based methods which leverage either node similarities or latent group memberships towards link prediction. Chen and Zhang recently developed a class of non-embedding approaches called Weisfeiler-Leman (WL) Models. WL-Models extract subgraphs around links and then encode subgraph patterns via adjacency matrices using the so-called Palette-WL algorithm. A training stage then learns nonlinear graph topological features for link prediction. Chen and Zhang compared two WL-Models – a linear regression model (“WLLR”) and a neural networks model (“WLNM”) – against 12 different common link prediction schemes. In this paper, all author claims are validated for WLLR. Additionally, WLLR is tested against 22 additional embedding-based link prediction techniques arising from common neighbor-, path- and random walk-based schemes. WLLR is shown not to be superior when calculable. In fact, in 80% of the datasets where comparisons were possible, one of our added implementations proved superior.
Authors and Affiliations
Katie Brodhead
Keywords
Related Articles
- EP ID EP319463
- DOI 10.14569/IJACSA.2018.090603
- Views 114
- Downloads 0
Efficient Energy Utilization in Cloud Fog Environment
Cloud computing provides various kind of services like storage and processing that can be accessed on-demand when required. Despite its countless benefits, it incorporates some issues too that limits the full adaption of...
Dynamic Programming Inspired Genetic Programming to Solve Regression Problems
The candidate solution in traditional Genetic Pro-graming is evolved through prescribed number of generations using fitness measure. It has been observed that, improvement of GP on different problems is insignificant at...
Comparative Analysis of Support Vector Machine, Maximum Likelihood and Neural Network Classification on Multispectral Remote Sensing Data
Land cover classification is an essential process in many remote sensing applications. Classification based on supervised methods have been preferred by many due to its practicality, accuracy and objectivity compared to...
Securing and Monitoring of Bandwidth Usage in Multi-Agents Denial of Service Environment
The primary purpose of Denial of Service attack (DoS) is to cripple resources so that the resources are made unavailable to the legitimate users. Due to the inadequate monitoring of activities on the network, it has resu...
A Review of Blockchain based Educational Projects
Blockchain is a decentralized and shared dis-tributed ledger that records the transaction history done by totally different nodes within the whole network. The technology is practically used in the field of education for...