More Web Proxy on the site http://driver.im/

research-article

Temporal knowledge graphs reasoning with iterative guidance by temporal logical rules

Authors:

Mingzhuo ChenAuthors Info & Claims

Volume 621, Issue C

Pages 22 - 35

https://doi.org/10.1016/j.ins.2022.11.096

Published: 01 April 2023 Publication History

Abstract

Reasoning is essential for the development of large temporal knowledge graphs, which aim to infer new facts based on existing ones. Recent temporal knowledge graph reasoning methods mainly embed timestamps into low-dimensional spaces. These methods focus on entity reasoning, which cannot obtain the specific reasoning paths. More importantly, they ignore the logic and explanation of reasoning paths in temporal knowledge graphs (TKGs). To overcome this limitation, we propose a novel Temporal Logical reasoning Model, denoted as TLmod. This model represents a reasoning process that works through iterative guidance by temporal logical rules. More importantly, we propose two principles of temporal logical rules and define five types of temporal logical rules. Meanwhile, considering the diversity of temporal logical rules, we propose a pruning strategy for obtaining them and calculating the confidence score by combining traversing and random selection. Experimental results show that our model outperforms most metrics compared to prior state-of-the-art baselines across two benchmarks. In addition, analysis of the ablation experiment reveals the validity and importance of temporal logical rules in TKGs.

References

[1]

L. Bai, W. Yu, M. Chen, X. Ma, Multi-hop reasoning over paths in temporal knowledge graphs using reinforcement learning, Appl. Soft Comput. 103 (2021).

Digital Library

[2]

A. Bordes, N. Usunier, A. García-Durán, J. Weston, O. Yakhnenko, Translating Embeddings for Modeling Multi-relational Data, in Proceedings of the 27th NIPS, Lake Tahoe, Nevada, USA, 2013, pp. 2787-2795.

[3]

R. Das, S. Dhuliawala, M. Zaheer, L. Vilnis, I. Durugkar, A. Krishnamurthy, A. Smola, A. McCallum, Go for a walk and arrive at the answer: reasoning over paths in knowledge bases using reinforcement learning, in Proceedings of the 6th ICLR, Vancouver, BC, Canada, 2018, pp. 1-18.

[4]

S.S. Dasgupta, S.N. Ray, P.P. Talukdar, Hyte: hyperplane-based temporally aware knowledge graph embedding, in Proceedings of the 2018 EMNLP, Brussels, Belgium, 2018, pp. 2001-2011.

[5]

B. Elizabeth, L. Jennifer, O. Sean, S. Steve, S. James, W. Michael, ICEWS Coded Event Data (2015),.

[6]

A. García-Durán, S. Dumancic, M. Niepert, Learning sequence encoders for temporal knowledge graph completion, in Proceedings of the 2018 EMNLP, Brussels, Belgium, 2018, pp. 4816-4821.

[7]

S. Guo, Q. Wang, L. Wang, B. Wang, L. Guo, Knowledge graph embedding with iterative guidance from soft rules, in Proceedings of the 32nd AAAI, New Orleans, Louisiana, USA, 2018, pp. 4816-4823.

[8]

S. Ji, S. Pan, E. Cambria, P. Marttinen, P.S. Yu, A survey on knowledge graphs: Representation, acquisition and applications, IEEE Trans. Neural Networks Learn. Syst. 33 (2) (2022) 494–514.

[9]

Z. Jia, A. Abujabal, R. Roy, J. Strötgen, and G. Weikumet, Tequila: Temporal question answering over knowledge bases, in Proceedings of the 27th CIKM, Torino, Italy, 2018, pp. 1807-1810.

[10]

W. Jin, C. Zhang, P. Szekely, X. Ren, “Recurrent event network for reasoning over temporal knowledge graphs,” in Proceedings of ICLR RLGM Workshop, 2019.

[11]

S.M. Kazemi, R. Goel, K. Jain, I. Kobyzev, A. Sethi, P. Forsyth, Poupart, Relational representation learning for dynamic graphs: A survey, J. Mach. Learn. Res. 21 (70) (2020) 1–73.

[12]

J. Leblay, M.W. Chekol, Deriving validity time in knowledge graph, in Proceedings of the 27th WWW, Lyon, France, 2018, pp. 1771-1776.

[13]

K. Leetaru, P. A. Schrodt, GDELT: Global data on events, location, and tone, 1979-2012, 2013.

[14]

Z. Li, X. Liu, X. Wang, P. Liu, Y. Shen, TransO: a knowledge-driven representation learning method with ontology information constraints, World Wide Web J. (2022) 1–23.

[15]

Y. Lin, Z. Liu, M. Sun, Y. Liu, X. Zhu, Learning entity and relation embeddings for knowledge graph completion, in Proceedings of the 29th AAAI, Austin, Texas, USA, 2015, pp. 2181-2187.

[16]

P. Liu, X. Wang, Q. Fu, Y. Yang, Y. Li, Q. Zhang, KGVQL: A knowledge graph visual query language with bidirectional transformations, Knowl.-Based Syst. 108870 (2022).

[17]

Y. Ma, V. Tresp, E.A. Daxberger, Embedding models for episodic knowledge graphs, J. Web Semantics 59 (2019).

[18]

G. Nguyen, J. Lee, R. A. Rossi, N. K. Ahmed, E. Koh, and S. Kim, Continuous-time dynamic network embeddings, in Proceedings of the 27th WWW, Lyon, France, 2018, pp. 969-976.

[19]

B. Shi, T. Weninger, ProjE: embedding projection for knowledge graph completion, in Proceedings of the 31st AAAI, San Francisco, California, USA, 2017, pp. 1236-1242.

[20]

Y. Song, Y. Qin, W. Hao, P. Liu, J. Li, F.M. Choudhury, X. Wang, Q. Zhang, Optimizing subgraph matching over distributed knowledge graphs using partial evaluation, World Wide Web J. (2022) 1–21.

[21]

R. Trivedi, H. Dai, Y. Wang, L. Song, Know-evolve: Deep temporal reasoning for dynamic knowledge graphs, in Proceedings of the 34st ICML, Sydney, NSW, Australia, 2018, pp. 3462-3471.

[22]

T. Trouillon, J. Welbl, S. Riedel, É. Gaussier, G. Bouchard, Complex embeddings for simple link prediction, in Proceedings of the 33rd ICML, New York City, USA, 2016, pp. 2071-2080.

[23]

Y. Wang, Z. Liu, Z Fan, L Sun, and P. Yu, DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN, in Proceedings of the 30th CIKM, Torino, Italy, 2021, pp. 3513-3517.

[24]

Z. Wang, J. Zhang, J. Feng, Z. Chen, Knowledge graph embedding by translating on hyperplanes, in Proceedings of the 28th AAAI, Québec City, Québec, Canada, 2014, pp. 1112-1119.

[25]

C. Xiong, V. Zhong, and R. Socher, Dynamic coattention networks for question answering, in Proceedings of the 5th ICLR, Palo Alto, USA, 2017, pp. 1-14.

[26]

W. Xiong, T. Hoang, W.Y. Wang, DeepPath: a reinforcement learning method for knowledge graph reasoning, in Proceedings of the 2017 EMNLP, Copenhagen, Denmark, 2017, pp. 564-573.

[27]

C. Xu, F. Su, and J. Lehmann, Time-aware graph neural networks for entity alignment between temporal knowledge graphs, in Proceedings of the 2021 EMNLP, Brussels, Belgium, 2021, pp. 1-12.

[28]

B. Yang, W. Yih, X. He, J. Gao, L, Deng, Embedding entities and relations for learning and inference in knowledge bases, in Proceedings of the 3rd ICLR, San Diego, CA, USA, 2015, pp. 1-12.

[29]

W. Zhang, B. Paudel, L. Wang, J. Chen, H. Zhu, W. Zhang, A. Bernstein, H. Chen, Iteratively learning embeddings and rules for knowledge graph reasoning, in Proceedings of the 28th WWW, San Francisco, CA, USA, 2019, pp. 2366-2377.

Cited By

Zhong HYang DShi SWei LWang Y(2024)From data to insights: the application and challenges of knowledge graphs in intelligent auditJournal of Cloud Computing: Advances, Systems and Applications10.1186/s13677-024-00674-013:1Online publication date: 29-May-2024
https://dl.acm.org/doi/10.1186/s13677-024-00674-0
Mei XYang LJiang ZCai XGao DHan JPan S(2024)An Inductive Reasoning Model based on Interpretable Logical Rules over temporal knowledge graphNeural Networks10.1016/j.neunet.2024.106219174:COnline publication date: 1-Jun-2024
https://dl.acm.org/doi/10.1016/j.neunet.2024.106219
Liu RYin GLiu ZTian Y(2024)Reinforcement learning with time intervals for temporal knowledge graph reasoningInformation Systems10.1016/j.is.2023.102292120:COnline publication date: 1-Feb-2024
https://dl.acm.org/doi/10.1016/j.is.2023.102292
Show More Cited By

Index Terms

Temporal knowledge graphs reasoning with iterative guidance by temporal logical rules

Index terms have been assigned to the content through auto-classification.

Recommendations

Multi-hop temporal knowledge graph reasoning with temporal path rules guidance
Abstract
Temporal Knowledge graph (TKG) is a key component of artificial intelligence. In recent years, many large-scale temporal knowledge graphs have been produced and put into practical applications. At present, researchers have proposed many methods ...
An improving reasoning network for complex question answering over temporal knowledge graphs
Abstract
Question Answering Over Temporal Knowledge Graphs is an important topic in question answering, which aims to find an entity or timestamp to answer temporal reasoning questions from temporal knowledge graphs. Answering complex questions remains a ...
An Inductive Reasoning Model based on Interpretable Logical Rules over temporal knowledge graph
Abstract
Extrapolating future events based on historical information in temporal knowledge graphs (TKGs) holds significant research value and practical applications. In this field, the methods currently utilized can be classified as either embedding-based ...
Highlights
- Proposed a hybrid rule-based and embedding-based method for inductive reasoning.
- Integrated logical rules inherent in relations with interaction preferences.
- Demonstrated zero-shot transferability of the proposed method on related ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Information Sciences: an International Journal

Information Sciences: an International Journal Volume 621, Issue C

Apr 2023

858 pages

ISSN:0020-0255

Issue’s Table of Contents

Elsevier Inc.

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 01 April 2023

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 31 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Zhong HYang DShi SWei LWang Y(2024)From data to insights: the application and challenges of knowledge graphs in intelligent auditJournal of Cloud Computing: Advances, Systems and Applications10.1186/s13677-024-00674-013:1Online publication date: 29-May-2024
https://dl.acm.org/doi/10.1186/s13677-024-00674-0
Mei XYang LJiang ZCai XGao DHan JPan S(2024)An Inductive Reasoning Model based on Interpretable Logical Rules over temporal knowledge graphNeural Networks10.1016/j.neunet.2024.106219174:COnline publication date: 1-Jun-2024
https://dl.acm.org/doi/10.1016/j.neunet.2024.106219
Liu RYin GLiu ZTian Y(2024)Reinforcement learning with time intervals for temporal knowledge graph reasoningInformation Systems10.1016/j.is.2023.102292120:COnline publication date: 1-Feb-2024
https://dl.acm.org/doi/10.1016/j.is.2023.102292
Xiao YZhou GXie ZLiu JHuang J(2024)Learning dual disentangled representation with self-supervision for temporal knowledge graph reasoningInformation Processing and Management: an International Journal10.1016/j.ipm.2023.10361861:3Online publication date: 2-Jul-2024
https://dl.acm.org/doi/10.1016/j.ipm.2023.103618
Qian YSun FWang XPan L(2024)TODEARInformation Sciences: an International Journal10.1016/j.ins.2024.121066679:COnline publication date: 1-Sep-2024
https://dl.acm.org/doi/10.1016/j.ins.2024.121066
Du CLi XLi Z(2024)Semantic-enhanced reasoning question answering over temporal knowledge graphsJournal of Intelligent Information Systems10.1007/s10844-024-00840-562:3(859-881)Online publication date: 1-Jun-2024
https://dl.acm.org/doi/10.1007/s10844-024-00840-5
Li PZhang SZhou GYin ZChen R(2023)A Semantically Enhanced Knowledge Discovery Method for Knowledge Graph Based on Adjacency Fuzzy Predicates ReasoningInternational Journal on Semantic Web & Information Systems10.4018/IJSWIS.32392119:1(1-24)Online publication date: 1-Jun-2023
https://dl.acm.org/doi/10.4018/IJSWIS.323921
Cai BXiang YGao LZhang HLi YLi JElkind E(2023)Temporal knowledge graph completionProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/734(6545-6553)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/734

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents