Multi-relational Poincaré Graph Embeddings

Ivana Balaževic; Carl Allen; Timothy Hospedales

Multi-relational Poincaré Graph Embeddings

Ivana Balaževic, Carl Allen, Timothy Hospedales

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Hyperbolic embeddings have recently gained attention in machine learning due to their ability to represent hierarchical data more accurately and succinctly than their Euclidean analogues. However, multi-relational knowledge graphs often exhibit multiple simultaneous hierarchies, which current hyperbolic models do not capture. To address this, we propose a model that embeds multi-relational graph data in the Poincaré ball model of hyperbolic space. Our Multi-Relational Poincaré model (MuRP) learns relation-specific parameters to transform entity embeddings by Möbius matrix-vector multiplication and Möbius addition. Experiments on the hierarchical WN18RR knowledge graph show that our Poincaré embeddings outperform their Euclidean counterpart and existing embedding methods on the link prediction task, particularly at lower dimensionality.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems (NIPS 2019)
Publisher	Curran Associates Inc
Pages	4465-4475
Number of pages	11
Volume	32
Publication status	Published - 14 Dec 2019
Event	33rd Conference on Neural Information Processing Systems - Vancouver Convention Centre, Vancouver, Canada Duration: 8 Dec 2019 → 14 Dec 2019 https://neurips.cc/

Conference

Conference	33rd Conference on Neural Information Processing Systems
Abbreviated title	NeurIPS 2019
Country/Territory	Canada
City	Vancouver
Period	8/12/19 → 14/12/19
Internet address	https://neurips.cc/

Access to Document

Multi-relational Poincare_BALAZEVIC_DOA03092019_AFVAccepted author manuscript, 1.75 MB

https://papers.nips.cc/paper/8696-multi-relational-poincare-graph-embeddingsLicence: All Rights Reserved

Cite this

@inproceedings{aca9bad386a245ba92fc24cc4e5d4f02,

title = "Multi-relational Poincar{\'e} Graph Embeddings",

abstract = "Hyperbolic embeddings have recently gained attention in machine learning due to their ability to represent hierarchical data more accurately and succinctly than their Euclidean analogues. However, multi-relational knowledge graphs often exhibit multiple simultaneous hierarchies, which current hyperbolic models do not capture. To address this, we propose a model that embeds multi-relational graph data in the Poincar{\'e} ball model of hyperbolic space. Our Multi-Relational Poincar{\'e} model (MuRP) learns relation-specific parameters to transform entity embeddings by M{\"o}bius matrix-vector multiplication and M{\"o}bius addition. Experiments on the hierarchical WN18RR knowledge graph show that our Poincar{\'e} embeddings outperform their Euclidean counterpart and existing embedding methods on the link prediction task, particularly at lower dimensionality.",

author = "Ivana Bala{\v z}evic and Carl Allen and Timothy Hospedales",

year = "2019",

month = dec,

day = "14",

language = "English",

volume = "32",

pages = "4465--4475",

booktitle = "Advances in Neural Information Processing Systems (NIPS 2019)",

publisher = "Curran Associates Inc",

note = "33rd Conference on Neural Information Processing Systems, NeurIPS 2019 ; Conference date: 08-12-2019 Through 14-12-2019",

url = "https://neurips.cc/",

}

Balaževic, I, Allen, C & Hospedales, T 2019, Multi-relational Poincaré Graph Embeddings. in Advances in Neural Information Processing Systems (NIPS 2019). vol. 32, Curran Associates Inc, pp. 4465-4475, 33rd Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, 8/12/19. <https://papers.nips.cc/paper/8696-multi-relational-poincare-graph-embeddings>

TY - GEN

T1 - Multi-relational Poincaré Graph Embeddings

AU - Balaževic, Ivana

AU - Allen, Carl

AU - Hospedales, Timothy

PY - 2019/12/14

Y1 - 2019/12/14

N2 - Hyperbolic embeddings have recently gained attention in machine learning due to their ability to represent hierarchical data more accurately and succinctly than their Euclidean analogues. However, multi-relational knowledge graphs often exhibit multiple simultaneous hierarchies, which current hyperbolic models do not capture. To address this, we propose a model that embeds multi-relational graph data in the Poincaré ball model of hyperbolic space. Our Multi-Relational Poincaré model (MuRP) learns relation-specific parameters to transform entity embeddings by Möbius matrix-vector multiplication and Möbius addition. Experiments on the hierarchical WN18RR knowledge graph show that our Poincaré embeddings outperform their Euclidean counterpart and existing embedding methods on the link prediction task, particularly at lower dimensionality.

AB - Hyperbolic embeddings have recently gained attention in machine learning due to their ability to represent hierarchical data more accurately and succinctly than their Euclidean analogues. However, multi-relational knowledge graphs often exhibit multiple simultaneous hierarchies, which current hyperbolic models do not capture. To address this, we propose a model that embeds multi-relational graph data in the Poincaré ball model of hyperbolic space. Our Multi-Relational Poincaré model (MuRP) learns relation-specific parameters to transform entity embeddings by Möbius matrix-vector multiplication and Möbius addition. Experiments on the hierarchical WN18RR knowledge graph show that our Poincaré embeddings outperform their Euclidean counterpart and existing embedding methods on the link prediction task, particularly at lower dimensionality.

M3 - Conference contribution

VL - 32

SP - 4465

EP - 4475

BT - Advances in Neural Information Processing Systems (NIPS 2019)

PB - Curran Associates Inc

T2 - 33rd Conference on Neural Information Processing Systems

Y2 - 8 December 2019 through 14 December 2019

ER -

Multi-relational Poincaré Graph Embeddings

Abstract

Conference

Access to Document

Fingerprint

Cite this