# Heterogeneous Relational Reasoning in Knowledge Graphs with Reinforcement Learning

Source: [Heterogeneous Relational Reasoning in Knowledge Graphs with Reinforcement Learning](<https://www.sota2.com/research/paper/68fa67391e209131cea1506a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:42.249Z

Authors: Mandana Saebi, Steven Krieg, Chuxu Zhang, Meng Jiang, Nitesh Chawla

Published: 2020-03-12T22:39:58.000Z

## Abstract

Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommender systems. In recent years, reinforcement learning (RL) has provided solutions that are more interpretable and explainable than other deep learning models. However, these solutions still face several challenges, including large action space for the RL agent and accurate representation of entity neighborhood structure. We address these problems by introducing a type-enhanced RL agent that uses the local neighborhood information for efficient path-based reasoning over knowledge graphs. Our solution uses graph neural network (GNN) for encoding the neighborhood information and utilizes entity types to prune the action space. Experiments on real-world dataset show that our method outperforms state-of-the-art RL methods and discovers more novel paths during the training procedure.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2003.06050>)

[PDF](<https://arxiv.org/pdf/2003.06050.pdf>)
