PolygonE: Modeling N-ary Relational Data as Gyro-Polygons in Hyperbolic Space

Authors

  • Shiyao Yan Aerospace Information Research Institute, Chinese Academy of Sciences Key Laboratory of Network Information System Technology(NIST), Aerospace Information Research Institute School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences
  • Zequn Zhang Aerospace Information Research Institute, Chinese Academy of Sciences Key Laboratory of Network Information System Technology(NIST), Aerospace Information Research Institute
  • Xian Sun Aerospace Information Research Institute, Chinese Academy of Sciences Key Laboratory of Network Information System Technology(NIST), Aerospace Information Research Institute
  • Guangluan Xu Aerospace Information Research Institute, Chinese Academy of Sciences Key Laboratory of Network Information System Technology(NIST), Aerospace Information Research Institute
  • Shuchao Li Aerospace Information Research Institute, Chinese Academy of Sciences Key Laboratory of Network Information System Technology(NIST), Aerospace Information Research Institute
  • Qing Liu Aerospace Information Research Institute, Chinese Academy of Sciences Key Laboratory of Network Information System Technology(NIST), Aerospace Information Research Institute
  • Nayu Liu Aerospace Information Research Institute, Chinese Academy of Sciences Key Laboratory of Network Information System Technology(NIST), Aerospace Information Research Institute School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences
  • Shensi Wang Aerospace Information Research Institute, Chinese Academy of Sciences Key Laboratory of Network Information System Technology(NIST), Aerospace Information Research Institute School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences

DOI:

https://doi.org/10.1609/aaai.v36i4.20351

Keywords:

Data Mining & Knowledge Management (DMKM)

Abstract

N-ary relational knowledge base (KBs) embedding aims to map binary and beyond-binary facts into low-dimensional vector space simultaneously. Existing approaches typically decompose n-ary relational facts into subtuples (entity pairs, triples or quintuples, etc.), and they generally model n-ary relational KBs in Euclidean space. However, n-ary relational facts are semantically and structurally intact, decomposition leads to the loss of global information and undermines the semantical and structural integrity. Moreover, compared to the binary relational KBs, n-ary ones are characterized by more abundant and complicated hierarchy structures, which could not be well expressed in Euclidean space. To address the issues, we propose a gyro-polygon embedding approach to realize n-ary fact integrity keeping and hierarchy capturing, termed as PolygonE. Specifically, n-ary relational facts are modeled as gyro-polygons in the hyperbolic space, where we denote entities in facts as vertexes of gyro-polygons and relations as entity translocation operations. Importantly, we design a fact plausibility measuring strategy based on the vertex-gyrocentroid geodesic to optimize the relation-adjusted gyro-polygon. Extensive experiments demonstrate that PolygonE shows SOTA performance on all benchmark datasets, generalizability to binary data, and applicability to arbitrary arity fact. Finally, we also visualize the embedding to help comprehend PolygonE's awareness of hierarchies.

Downloads

Published

2022-06-28

How to Cite

Yan, S., Zhang, Z., Sun, X., Xu, G., Li, S., Liu, Q., Liu, N., & Wang, S. (2022). PolygonE: Modeling N-ary Relational Data as Gyro-Polygons in Hyperbolic Space. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 4308-4317. https://doi.org/10.1609/aaai.v36i4.20351

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management