# Clustering-Based Relational Unsupervised Representation Learning with an Explicit Distributed Representation

arXiv: https://arxiv.org/abs/1606.08658 · HTML: https://mlsanity.com/paper/1606.08658/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2016.

## Built on by (most cited first, 3 of 3)

- [Inductive logic programming at 30](https://mlsanity.com/paper/2102.10556/) (2021)
- [Predicate Invention by Learning From Failures](https://mlsanity.com/paper/2104.14426/) (2021)
- [Rule Learning by Modularity](https://mlsanity.com/paper/2212.12335/) (2022)

## Abstract (arXiv)

The goal of unsupervised representation learning is to extract a new representation of data, such that solving many different tasks becomes easier. Existing methods typically focus on vectorized data and offer little support for relational data, which additionally describe relationships among instances. In this work we introduce an approach for relational unsupervised representation learning. Viewing a relational dataset as a hypergraph, new features are obtained by clustering vertices and hyperedges. To find a representation suited for many relational learning tasks, a wide range of similarities between relational objects is considered, e.g. feature and structural similarities. We experimentally evaluate the proposed approach and show that models learned on such latent representations perform better, have lower complexity, and outperform the existing approaches on classification tasks.