Home  | Publications | FBB+20

Ada-LLD: Adaptive Node Similarity Using Multi-Scale Local Label Distributions

MCML Authors

Link to Profile Matthias Schubert PI Matchmaking

Matthias Schubert

Prof. Dr.

Principal Investigator

Spatial Artificial Intelligence

Abstract

In many applications, data is represented as a network connecting nodes of various types. While types might be known for some nodes in the network, the type of a newly added node is typically unknown. In this paper, we focus on predicting the types of these new nodes based on their connectivity to the already labeled nodes. To tackle this problem, we propose Adaptive Node Similarity Using Multi-Scale Local Label Distributions (Ada-LLD) which learns the dependency of a node’s class label from the distribution of class labels in this node’s local neighborhood. In contrast to previous approaches, our approach is able to learn how class labels correlate with labels in variously sized neighborhoods. We propose a neural network architecture that combines information from differently sized neighborhoods allowing for the detection of correlations on multiple scales. Our evaluations demonstrate that our method significantly improves prediction quality on real world data sets. In the spirit of reproducible research we make our code available.

inproceedings

WI-IAT 2020

IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology. Virtual, Dec 14-17, 2020.

Authors

E. Faerman • F. Borutta • J. Busch • M. Schubert

Links

DOI GitHub

Research Area

 A3 | Computational Models

BibTeXKey: FBB+20

Back to Top