Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic Trajectories

Mojtaba Nayyeri, Bo Xiong, Majid Mohammadi, Mst. Mahfuja Akter, Mirza Mohtashim Alam, Jens Lehmann, Steffen Staab

Abstract
Knowledge graphs mostly exhibit a mixture of branching relations, e.g., hasFriend, and complex structures, e.g., hierarchy and loop. Most knowledge graph embeddings have problems expressing them, because they model a specific relation r from a head h to tails by starting at the node embedding of h and transitioning deterministically to exactly one other point in the embedding space. We overcome this issue in our novel framework ItCAREToE by modeling relations between nodes by relation-specific, stochastic transitions. Our framework is based on stochastic ItCARETo processes, which operate on low-dimensional manifolds. ItCAREToE is highly expressive and generic subsuming various state-of-the-art models operating on different, also non-Euclidean, manifolds. Experimental results show the superiority of ItCAREToE over other deterministic embedding models with regard to the KG completion task.
Anthology ID:
2023.findings-acl.448
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7165–7179
Language:
URL:
https://aclanthology.org/2023.findings-acl.448
DOI:
10.18653/v1/2023.findings-acl.448
Bibkey:
Cite (ACL):
Mojtaba Nayyeri, Bo Xiong, Majid Mohammadi, Mst. Mahfuja Akter, Mirza Mohtashim Alam, Jens Lehmann, and Steffen Staab. 2023. Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic Trajectories. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7165–7179, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic Trajectories (Nayyeri et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-acl.448.pdf
PDF Search