Shuwen Liu
Interests
My research interests revolve around the fields of knowledge representation and graph representation learning. Throughout my PhD studies, I am primarily motivated by the interconnections between Knowledge Graphs (KGs) and Graph Neural Networks (GNNs). My overarching objective is to exploit the power of GNNs to enhance the quality of KGs through KG completion, as well as incorporate the semantic information in KGs for applications such as recommender systems. Moreover, I am also interested in investigating the capability of machine learning models to make logical inferences.
Biography
I am a DPhil student (Oct 2019 to Present) in the Department of Computer Science at University of Oxford. I am fortunately supervised by Professor Ian Horrocks, Professor Bernardo Cuenca Grau, and Professor Egor Kostylev. Prior to that, I obtained my Bachelor degree in Information Management and Information System from Peking University, China.
Selected Publications
-
Revisiting Inferential Benchmarks for Knowledge Graph Completion
Shuwen Liu‚ Bernardo Cuenca Grau‚ Ian Horrocks and Egor V. Kostylev
In Proceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning‚ KR 2023‚ Rhodes‚ Greece‚ September 2−8‚ 2023. 2023.
Details about Revisiting Inferential Benchmarks for Knowledge Graph Completion | BibTeX data for Revisiting Inferential Benchmarks for Knowledge Graph Completion
-
INDIGO: GNN−Based Inductive Knowledge Graph Completion Using Pair−Wise Encoding
Shuwen Liu‚ Bernardo Cuenca Grau‚ Ian Horrocks and Egor V. Kostylev
In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2021‚ NeurIPS 2021‚ December 6−14‚ 2021. 2021.
Details about INDIGO: GNN−Based Inductive Knowledge Graph Completion Using Pair−Wise Encoding | BibTeX data for INDIGO: GNN−Based Inductive Knowledge Graph Completion Using Pair−Wise Encoding