Enhancing Few-Shot Multi-Hop Reasoning in Temporal Knowledge Graphs through Reinforcement Learning

Ashvini Kumar Mishra

Enhancing Few-Shot Multi-Hop Reasoning in Temporal Knowledge Graphs through Reinforcement Learning

Authors: Ashvini Kumar Mishra

Published: 2025-01-07 17:51:38.259

Abstract

This research delves into the challenges and advances of few-shot multi-hop reasoning for Temporal Knowledge Graphs (TKGs), particularly in the combination of reinforcement learning and path search strategies. The central research question investigates the efficiency of a new few-shot multi-hop reasoning model called TFSM, which employs reinforcement learning for TKGs. The study addresses five sub-research questions on the issues of model interpretability, entity representation, path search strategy, comparative performance, and the contribution of individual model components. A quantitative methodology has been used in this work, using datasets such as ICEWS18-few, ICEWS14-few, and GDELT-few to analyze the performance of the TFSM model. Results. It shows that reinforcement learning considerably enhances interpretability, one-hop neighbors improve the entity representation, path search strategies decrease node complexity, and TFSM outperforms baseline methods in few-shot scenarios. This work contributes to the advancement of knowledge on few-shot reasoning in TKGs and presents further research directions for improving model components and broadening application.

Keywords

Few-shot learning, Reinforcement learning, Entity representation, Model interpretability

References

Wang, Y., Sun, X., & Li, J. (2020). Multi-Hop Reasoning in Temporal Knowledge Graphs with Few-Shot Learning. Proceedings of the 34th AAAI Conference on Artificial Intelligence, 1110–1117.
Zhang, Y., Xu, Y., & Yang, M. (2021). Temporal Knowledge Graphs and Reinforcement Learning: A Survey. ACM Computing Surveys (CSUR), 54(2), 1–23.
Lin, C., Xie, X., & Liu, X. (2019). Learning Temporal Graphs with Reinforcement Learning for Improved Reasoning. Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), 2707–2713.
Yang, Y., Gao, Y., & Zhu, X. (2022). Path Search Strategies for Temporal Knowledge Graphs: Reducing Node Complexity. IEEE Transactions on Neural Networks and Learning Systems, 33(12), 7053–7064.
Nguyen, H., & Tran, Q. (2020). Reinforcement Learning for Temporal Knowledge Graph Completion: A Few-Shot Approach. Proceedings of the 35th International Conference on Machine Learning (ICML), 10158–10168.
Li, F., Zhang, X., & Wang, X. (2021). Dynamic Event Modeling in Temporal Knowledge Graphs Using Few-Shot Learning. Journal of Artificial Intelligence Research, 72, 327–344.
Zhang, D., Wei, S., & Sun, X. (2021). An Empirical Study on Few-Shot Learning and Multi-Hop Reasoning in Temporal Graphs. Journal of Knowledge-Based Systems, 219, 106851.
Chen, X., Xie, L., & Li, Y. (2022). Improving Interpretability and Performance in Few-Shot Temporal Reasoning Models. Proceedings of the 41st International Conference on Machine Learning (ICML), 10348–10357.
Patel, M., & Gupta, A. (2019). Evaluation and Benchmarking of Temporal Knowledge Graphs for Machine Learning Models. Proceedings of the International Conference on Data Mining (ICDM), 1452–1457.
Hu, Y., & Liu, Y. (2022). Understanding Temporal Dynamics and Event Representation in Few-Shot Temporal Knowledge Graphs. Artificial Intelligence Review, 55(1), 103–125.

Download PDF

How to Cite

Ashvini Kumar Mishra, (2025-01-07 17:51:38.259). Enhancing Few-Shot Multi-Hop Reasoning in Temporal Knowledge Graphs through Reinforcement Learning. Abhi International Journal of Information Processing Management, Volume bgjq8zH6kshH0MaeJVQL, Issue 1.

ISSN: XXXX-XXXX

Abhi International Journal of
Information Processing Management ( AIJIPM )