Multi-task Neural Network for Non-discrete Attribute Prediction in Knowledge Graphs

TL;DR

This paper introduces a multi-task neural network that effectively encodes and predicts non-discrete attributes in knowledge graphs, improving relational triplet classification and attribute value prediction accuracy.

Contribution

It presents a novel multi-task neural network approach that jointly encodes and predicts non-discrete attribute information in knowledge graphs, addressing data sparsity and incompleteness.

Findings

Outperforms state-of-the-art methods in triplet classification

Achieves higher accuracy in attribute value prediction

Effectively encodes entity, relation, and attribute information

Abstract

Many popular knowledge graphs such as Freebase, YAGO or DBPedia maintain a list of non-discrete attributes for each entity. Intuitively, these attributes such as height, price or population count are able to richly characterize entities in knowledge graphs. This additional source of information may help to alleviate the inherent sparsity and incompleteness problem that are prevalent in knowledge graphs. Unfortunately, many state-of-the-art relational learning models ignore this information due to the challenging nature of dealing with non-discrete data types in the inherently binary-natured knowledge graphs. In this paper, we propose a novel multi-task neural network approach for both encoding and prediction of non-discrete attribute information in a relational setting. Specifically, we train a neural network for triplet prediction along with a separate network for attribute value regression. Via multi-task learning, we are able to learn representations of entities, relations and attributes that encode information about both tasks. Moreover, such attributes are not only central to many predictive tasks as an information source but also as a prediction target. Therefore, models that are able to encode, incorporate and predict such information in a relational learning context are highly attractive as well. We show that our approach outperforms many state-of-the-art methods for the tasks of relational triplet classification and attribute value prediction.