@inproceedings{wang2022multi-level,
author = {Wang, Xiting and Liu, Kunpeng and Wang, Dongjie and Wu, Le and Fu, Yanjie and Xie, Xing},
title = {Multi-level Recommendation Reasoning over Knowledge Graphs with Reinforcement Learning},
booktitle = {The Web Conference 2022},
year = {2022},
month = {April},
abstract = {Knowledge graphs (KGs) have been widely used to improve recommendation accuracy. The multi-hop paths on KGs also enable recommendation reasoning, which is considered a crystal type of explainability. In this paper, we propose a reinforcement learning framework for multi-level recommendation reasoning over KGs, which leverages both ontology-view and instance-view KGs to model multi-level user interests. This framework ensures convergence to a more satisfying solution by effectively transferring high-level knowledge to lower levels. Based on the framework, we propose a multi-level reasoning path extraction method, which automatically selects between high-level concepts and low-level ones to form reasoning paths that better reveal user interests. Experiments on three datasets demonstrate the effectiveness of our method.},
url = {http://approjects.co.za/?big=en-us/research/publication/multi-level-recommendation-reasoning-over-knowledge-graphs-with-reinforcement-learning/},
}