Learning Context-based Embeddings for Knowledge Graph Completion Cover

.blurhash-client-img { display: none !important; }

Learning Context-based Embeddings for Knowledge Graph Completion

Journal of Data and Information Science

Volume 7 (2022): Issue 2 (April 2022)

By: Fei Pu, Zhongwei Zhang, Yan Feng and Bailin Yang

Open Access

|Apr 2022

Figures & Tables

Testing the ability of inferring relation patterns on UMLS_

	UMLS

	Symmetry	Antisymmetry	Inversion	Composition
ComplEx	-	0.8806	0.8615	0.8732
Rotate	-	0.9065	0.9069	0.9141
HAKE	-	0.8558	0.8650	0.8723
LineaRE	-	0.9446	0.9441	0.9490
ContE	-	0.9644	0.9622	0.9645

Experimental results for Nations_

	Nations

	MRR	Hits@N

		1	3	10
TransE (Antoine et al., 2013)	0.4813	0.2189	0.6667	0.9801
DistMult (Yang et al., 2015)	0.7131	0.5970	0.7761	0.9776
ComplEx (Trouillon et al., 2016)	0.6677	0.5274	0.7413	0.9776
ConvE (Dettmers et al., 2018)	0.5616	0.3470	0.7155	0.9946
Rotate (Sun et al., 2019)	0.7155	0.5796	0.7985	1.0
HAKE (Zhang et al., 2020)	0.7157	0.5945	0.7786	0.9851
LineaRE (Peng & Zhang, 2020)	0.8146	0.7114	0.8881	0.9975
ContE	0.8412	0.7587	0.9179	1.0

Comparison of SOTA baselines and ContE model in terms of time complexity and number of parameters_

Models	#Parameters	Time Complexity
TransE	O(n_ed + n_rd)	O(d)
NTN	O(n_ed + n_rd²k)	O(d³)
ComplEx	O(n_ed + n_rd)	O(d)
TransR	O(n_ed + n_rdk)	O(dk)
SimplE	O(n_ed + n_rd)	O(d)
ContE	O(n_ed + 2n_rd)	O(d)

Summary on datasets_

Dataset	\|E\|	\|R\|	\|training\|	\|validation\|	\|test\|
FB15K-237	14,541	237	272,115	17,535	20,466
UMLS	135	46	5,216	652	661
Nations	14	55	1,592	199	201
Countries_S1	271	2	1,111	24	24
Countries_S2	271	2	1,063	24	24
Countries_S3	271	2	985	24	24

Experimental results for FB15K-237_

	FB15K-237

	MRR	Hits@N

		1	3	10
TransE (Antoine et al., 2013)	0.279	0.198	0.376	0.441
DistMult (Yang et al., 2015)	0.281	0.199	0.301	0.446
ComplEx (Trouillon et al., 2016)	0.278	0.194	0.297	0.45
ConvE (Dettmers et al., 2018)	0.312	0.225	0.341	0.497
ConvKB (Nguyen et al., 2018)	0.289	0.198	0.324	0.471
R-GCN (Schlichtkrull et al., 2018)	0.164	0.10	0.181	0.30
SimplE (Seyed & David, 2018)	0.169	0.095	0.179	0.327
CapsE (Nguyen et al., 2019)	0.150	-	-	0.356
Rotate (Sun et al., 2019)	0.338	0.241	0.375	0.533
ContE	0.3445	0.2454	0.3823	0.5383

Experimental results for UMLS_

	UMLS

	MRR	Hits@N

		1	3	10
TransE (Antoine et al., 2013)	0.7966	0.6452	0.9418	0.9841
DistMult (Yang et al., 2015)	0.868	0.821	-	0.967
ComplEx (Trouillon et al., 2016)	0.8753	0.7942	0.9531	0.9713
ConvE (Dettmers et al., 2018)	0.957	0.932	-	0.994
NeuralLP (Yang, Zhang, & Cohen, 2017)	0.778	0.643	-	0.962
NTP-λ (Rocktaschel et al., 2017)	0.912	0.843	-	1.0
MINERVA (Das et al., 2018)	0.825	0.728	-	0.968
KGRRS+ComplEx (Lin et al., 2018)	0.929	0.887	-	0.985
KGRRS+ConvE (Lin et al., 2018)	0.940	0.902	-	0.992
Rotate (Sun et al., 2019)	0.9274	0.8744	0.9788	0.9947
HAKE (Zhang et al., 2020)	0.8928	0.8366	0.9387	0.9849
LineaRE (Peng & Zhang, 2020)	0.9508	0.9145	0.9856	0.9992
ContE	0.9677	0.9501	0.9811	1.0

Parameters and scoring functions in SOTA baselines and in ContE model_

Model	Scoring function ψ(e₁,r,e₂)	Parameters
TransE	\|\|ν_e₁ + ν_r − ν_e₂\|\|_{_p}	ν_e₁, ν_r, ν_e₂ ∈ ℝ^d
ComplEx	Re(<νe1,νr,ν¯e2>) {{ Re}} \left( { < {\nu _{{e_1}}},{\nu _r},{{\bar \nu }_{{e_2}}} > } \right)	ν_e₁, ν_r, ν_e₂ ∈ ℂ^d
SimplE	12(<he1,νr,te2>+<he2,νr−1,te1>) {1 \over 2}\left( { < {h_{{e_1}}},{\nu _r},{t_{{e_2}}} > + < {h_{{e_2}}},{\nu _{{r^{ - 1}}}},{t_{{e_1}}} > } \right)	h_e₁, ν_r, t_e₂, h_e₂, ν_r⁻¹, t_e₁ ∈ ℝ^d
ConvE	g(vec(g(concat(v^e1,νr)Ω))W)⋅νe2 g\left( {vec\left( {g\left( {concat\left( {{{\hat v}_{{e_1}}},{\nu _r}} \right)\Omega } \right)} \right)W} \right) \cdot {\nu _{{e_2}}}	ν_e₁, ν_r, ν_e₂ ∈ ℝ^d
ConvKB	concat(g([ν_e₁, ν_r, ν_e₂] * Ω)) · w	ν_e₁, ν_r, ν_e₂ ∈ ℂ^d
Rotate	\|\|ν_e₁ ○ ν_r − ν_e₂\|\|	ν_e₁, ν_e₂, ν_r, ∈ C^d
HAKE	\|\|ν_{e1_m} ○ ν_{r_m} − ν_{e2_m}\|\|₂	νe1m,νe2m∈Rd,νrm∈R+d {\nu _{e{1_m}}},{\nu _{e{2_m}}} \in {R^d},{\nu _{{r_m}}} \in R_ + ^d
HAKE	−λ \|\|sin(ν_{e1_p} + ν_{r_p} − ν_{e2_p})\|\|₁	ν_{e1_p}, r_p, ν_{e2_p} ∈ [0, 2π)^d
ContE	< f_r + ν_e₁, b_r + ν_e₂ >	ν_e₁, ν_e₂, f_r, b_r, ∈ ℝ^d

Experimental results for Countries_S2 and Countries_S3_

	Countries_S2				Countries_S3

	MRR	Hits@N			MRR	Hits@N

		1	3	10		1	3	10
TransE	0.6997	0.50	0.9375	1.0	0.1206	0.00	0.0833	0.3542
DistMult	0.7813	0.5833	1.0	1.0	0.2496	0.0625	0.333	0.6250
ComplEx	0.7934	0.6042	0.9792	1.0	0.2731	0.0833	0.3958	0.6667
Rotate	0.6979	0.4792	0.9583	1.0	0.1299	0.00	0.0833	0.4792
HAKE	0.6667	0.4583	0.8333	0.9583	0.2472	0.0625	0.3333	0.5417
LineaRE	0.7873	0.6458	0.9583	0.9792	0.2393	0.0625	0.3542	0.5208
ContE	0.8370	0.7292	0.9583	0.9792	0.4695	0.3542	0.5	0.625

Relation pattern modeling and inference abilities of baseline models_

Model	Symmetry	Antisymmetry	Inversion	Composition
TransE (Antoine et al., 2013)	×	✓	✓	✓
DistMult (Yang et al., 2015)	✓	×	×	×
ComplEx (Trouillon et al., 2016)	✓	✓	✓	×
SimplE (Seyed & David, 2018)	✓	✓	✓	×
ConvE (Dettmers et al., 2018)	−	−	−	−
ConvKB (Nguyen et al., 2018)	−	−	−	−
RotatE (Sun et al., 2019)	✓	✓	✓	✓
HAKE (Zhang et al., 2020)	✓	✓	✓	✓
KGCR (Pu et al., 2020)	✓	✓	✓	×
LineaRE (Peng & Zhang, 2020)	✓	✓	✓	✓
ContE	✓	✓	✓	✓

Experimental results for Countries_S1_

	Countries_S1

	MRR	Hits@N

		1	3	10
TransE (Antoine et al., 2013)	0.8785	0.7708	1.0	1.0
DistMult (Yang et al., 2015)	0.9028	0.8125	1.0	1.0
ComplEx (Trouillon et al., 2016)	0.9792	0.9583	1.0	1.0
Rotate (Sun et al., 2019)	0.8750	0.7708	1.0	1.0
HAKE (Zhang et al., 2020)	0.9045	0.8333	0.9792	1.0
LineaRE (Peng & Zhang, 2020)	1.0	1.0	1.0	1.0
ContE	1.0	1.0	1.0	1.0

Testing the ability of inferring relation patterns on Nations_

	Nations

	Symmetry	Antisymmetry	Inversion	Composition
ComplEx	-	0.6499	0.6487	0.6499
Rotate	-	0.6825	0.6970	0.6907
HAKE	-	0.6953	0.6835	0.6844
LineaRE	-	0.8189	0.8240	0.8333
ContE	-	0.8256	0.8326	0.8303

DOI: https://doi.org/10.2478/jdis-2022-0009 | Journal eISSN: 2543-683X | Journal ISSN: 2096-157X

Journal RSS Feed

Language: English

Page range: 84 - 106

Submitted on: Nov 3, 2021

Accepted on: Mar 10, 2022

Published on: Apr 25, 2022

Published by: Chinese Academy of Sciences, National Science Library

In partnership with: Paradigm Publishing Services

Publication frequency: 4 issues per year

Keywords:

Full expressiveness,

Relational contexts,

Knowledge graph embedding,

Relation patterns,

Link prediction

Related subjects:

Computer sciences,

Information technology,

Project management,

Databases and data mining

© 2022 Fei Pu, Zhongwei Zhang, Yan Feng, Bailin Yang, published by Chinese Academy of Sciences, National Science Library
This work is licensed under the Creative Commons Attribution 4.0 License.

Previous article Volume 7 (2022): Issue 2 (April 2022)