Neural RELAGGS

TL;DR

This paper introduces N-RELAGGS, a neural network-based propositionalization method for multi-relational data that learns aggregate functions, improving predictive performance over traditional RELAGGS and other algorithms.

Contribution

It presents a novel neural approach to propositionalization that learns aggregate functions jointly with prediction models, enhancing flexibility and accuracy.

Findings

N-RELAGGS outperforms RELAGGS in predictive tasks.

Learned aggregations can be used as embeddings in other models.

The method demonstrates improved accuracy on benchmark datasets.

Abstract

Multi-relational databases are the basis of most consolidated data collections in science and industry today. Most learning and mining algorithms, however, require data to be represented in a propositional form. While there is a variety of specialized machine learning algorithms that can operate directly on multi-relational data sets, propositionalization algorithms transform multi-relational databases into propositional data sets, thereby allowing the application of traditional machine learning and data mining algorithms without their modification. One prominent propositionalization algorithm is RELAGGS by Krogel and Wrobel, which transforms the data by nested aggregations. We propose a new neural network based algorithm in the spirit of RELAGGS that employs trainable composite aggregate functions instead of the static aggregate functions used in the original approach. In this way, we can jointly train the propositionalization with the prediction model, or, alternatively, use the learned aggegrations as embeddings in other algorithms. We demonstrate the increased predictive performance by comparing N-RELAGGS with RELAGGS and multiple other state-of-the-art algorithms.