Adjusted Count Quantification Learning on Graphs

Clemens Damke, Eyke Hüllermeier

Keywords: quantification learning, graph neural networks, distribution shift

TL;DR: We extend Quantification Learning to graphs and propose two new structure-based extensions to the Adjusted Count approach.

Abstract:

*Quantification learning* is the task of predicting the label distribution of a set of instances.
We study this problem in the context of graph-structured data, where the instances are vertices.
Previously, this problem has only been addressed via node clustering methods.
In this paper, we extend the popular *Adjusted Classify & Count* (ACC) method to graphs.
We show that the prior probability shift assumption upon which ACC relies is often not applicable to graph quantification problems.
To address this issue, we propose structural importance sampling (SIS), the first graph quantification method that is applicable under (structural) covariate shift.
Additionally, we propose Neighborhood-aware ACC, which improves quantification in the presence of non-homophilic edges.
We show the effectiveness of our techniques on multiple graph quantification tasks.

Primary Area: General machine learning (supervised, unsupervised, online, active, etc.)

Submission Number: 24888