Message Function Search for Knowledge Graph Embedding

Recently, many promising embedding models have been proposed to embed knowledge graphs (KGs) and their more general forms, such as n-ary relational data (NRD) and hyper-relational KG (HKG). To promote the data adaptability and performance of embedding models, KG searching methods propose to search for suitable models for a given KG data set. But they are restricted to a single KG form, and the searched models are restricted to a single type of embedding model. To tackle such issues, we propose to build a search space for the message function in graph neural networks (GNNs). However, it is a non-trivial task. Existing message function designs fx the structures and operators, which makes them difcult to handle diferent KG forms and data sets. Therefore, we frst design a novel message function space, which enables both structures and operators to be searched for the given KG form (including KG, NRD, and HKG) and data. The proposed space can fexibly take diferent KG forms as inputs and is expressive to search for diferent types of embedding models. Especially, some existing message function designs and some classic KG embedding models can be instantiated as special cases of our space. We empirically show that the searched message functions are data-dependent, and can achieve leading performance on benchmark KGs, NRD, and HKGs. CCS CONCEPTS • Information systems → Web searching and information discovery; • Computing methodologies → Knowledge representation and reasoning; Machine learning algorithms.