Learning Meta-Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction

Ding, Zifeng; He, Bailan ; Wu, Jingpei; Ma, Yunpu ; Han, Zhen und Tresp, Volker (2023): Learning Meta-Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction. International Joint Conference on Neural Networks (IJCNN), Gold Coast, Queensland, Australia, 18.-23. Juni 2023. IEEE Computational Intelligence Society, International Neural Network Society (INNS) (Hrsg.), In: IJCNN 2023 conference proceedings, Piscataway, NJ, USA: IEEE.

Abstract

Few-shot relational learning for static knowledge graphs (KGs) has drawn greater interest in recent years, while few-shot learning for temporal knowledge graphs (TKGs) has hardly been studied. Compared to KGs, TKGs contain rich temporal information, thus requiring temporal reasoning techniques for modeling. This poses a greater challenge in learning few-shot relations in the temporal context. In this paper, we follow the previous work that focuses on few-shot relational learning on static KGs and extend two fundamental TKG reasoning tasks, i.e., interpolated and extrapolated link prediction, to the one-shot setting. We propose four new large-scale benchmark datasets and develop a TKG reasoning model for learning one-shot relations in TKGs. Experimental results show that our model can achieve superior performance on all datasets in both TKG link prediction tasks.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Mathematik, Informatik und Statistik > Informatik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISBN: 978-1-6654-8867-9 ; 978-1-6654-8868-6
• Ort: Piscataway, NJ, USA
• Sprache: Englisch