# Demystifying Relational Latent Representations

## TL;DR

This paper demonstrates that relational latent features learned through clustering are interpretable, capture meaningful data properties, and can be optimized by removing redundancies without significant performance loss.

## Contribution

It shows that clustering-based relational latent features are interpretable, relevant to labels, and can be pruned to reduce redundancy while maintaining effectiveness.

## Key findings

- Latent features are interpretable and capture data properties.
- They identify local regions matching labels.
- Many features are redundant and can be removed.

## Abstract

Latent features learned by deep learning approaches have proven to be a powerful tool for machine learning. They serve as a data abstraction that makes learning easier by capturing regularities in data explicitly. Their benefits motivated their adaptation to relational learning context. In our previous work, we introduce an approach that learns relational latent features by means of clustering instances and their relations. The major drawback of latent representations is that they are often black-box and difficult to interpret. This work addresses these issues and shows that (1) latent features created by clustering are interpretable and capture interesting properties of data; (2) they identify local regions of instances that match well with the label, which partially explains their benefit; and (3) although the number of latent features generated by this approach is large, often many of them are highly redundant and can be removed without hurting performance much.