Abstract
Knowledge graph reasoning aims at solving certain tasks by finding reasoning paths, which has aroused extensive attention. Recently, a solution for path reasoning that combines reinforcement learning has achieved successful progress. But these researches mainly focus on the agent’s choice of relation and ignore the importance of entity, which will cause the random selection by the agent if 1-N/N-N relations occur. Thus, we propose a reinforcement learning based path reasoning model, which solves this problem from the topological and semantic levels. First, the attention mechanism is introduced in our model, which can extract the hidden feature from neighbor entities and helps the policy network to make a suitable choice instead of random for the actions with the same relation. Then, we introduce a convolutional neural network into our model to distinguish the rationality of the path by the semantic feature. To mitigate the negative impact of terminal rewards, we use a potential-based reward shaping function, which considers the potential gap between agent states as the reward and without any pre-training. Finally, we compare our model with the state-of-the-art baselines on two benchmark datasets, the results of extensive comparison experiments validate the effectiveness of the proposed method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Qiu, Y., Wang, Y., Jin, X., Zhang, K.: Stepwise reasoning for multi-relation question answering over knowledge graph with weak supervision. In: WSDM, pp. 474–482 (2020)
Xian, Y., Fu, Z., et al.: Reinforcement knowledge graph reasoning for explainable recommendation. In: SIGIR, pp. 285–294 (2019)
Xiong, W, Hoang, T, Wang, W Y.: Deeppath: a reinforcement learning method for knowledge graph reasoning. In: EMNLP, pp. 564–573 (2017)
Das, R., Dhuliawala, S., Zaheer, M., et al.: Go for a walk and arrive at the answer: reasoning over paths in knowledge bases using reinforcement learning. In: ICLR (2018)
Sutton, R.S., Andrew G.B.: Reinforcement learning: an introduction. MIT press (2018)
Li, Z., Jin, X., Guan, S., Wang, Y., Cheng, X.: Path reasoning over knowledge graph: a multi-agent and reinforcement learning based method. In: ICDMW, pp. 929–936 (2018)
Bordes, A., et al.: Translating embeddings for modeling multi-relational data. In: Advances in neural information processing systems, pp. 2787–2795 (2013)
Wang, Z., et al.: Knowledge graph embedding by translating on hyperplanes. In: AAAI, vol. 14, pp. 1112–1119 (2014)
Lin, Y., et al.: Learning entity and relation embeddings for knowledge graph completion. In: AAAI, vol. 15, pp. 2181–2187 (2015)
Jia, Y., et al.: Locally adaptive translation for knowledge graph embedding. In: AAAI, pp. 992–998 (2016)
Yang, B., Yih, W.T., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575 (2014)
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G.: Complex embeddings for simple link prediction. In: ICML, pp. 2071–2080 (2016)
Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2d knowledge graph embeddings. In: AAAI Conference on Artificial Intelligence. (2018)
Lao, N., Mitchell, T., Cohen, W.W.: Random walk inference and learning in a large scale knowledge base. In: EMNLP, pp. 529–539 (2011)
Lin, X.V., Socher, R., Xiong, C.: Multi-hop knowledge graph reasoning with reward shaping. In: EMNLP, pp. 3243–3253 (2018)
Li, R., Cheng, X.: DIVINE: a generative adversarial imitation learning framework for knowledge graph reasoning. In: EMNLP-IJCNLP, pp. 2642–2651 (2019)
Lei, D., Jiang, G., Gu, X., et al.: Learning collaborative agents with rule guidance for knowledge graph reasoning. In: EMNLP, pp. 8541–8547 (2020)
Minervini, P., Bošnjak, M., Rocktäschel, T., et al.: Differentiable reasoning on large knowledge bases and natural language. In: AAAI vol. 34, No. 04, pp. 5182–5190 (2020)
Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: ICML, pp. 278–287 (1999)
Gulrajani, I., Ahmed, F., Arjovsky, M., et al.: Improved training of wasserstein gans. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Acknowledgement
This work was in part supported by the Major project of IoV , Technological Innovation Projects in Hubei Province (Grant No. 2020AAA001, 2019AAA024) and Sanya Science and Education Innovation Park of Wuhan University of Technology (Grant No. 2020KF0054).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, S., Chen, X., Xiong, S. (2021). Attention Based Reinforcement Learning with Reward Shaping for Knowledge Graph Reasoning. In: Wang, L., Feng, Y., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2021. Lecture Notes in Computer Science(), vol 13028. Springer, Cham. https://doi.org/10.1007/978-3-030-88480-2_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-88480-2_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88479-6
Online ISBN: 978-3-030-88480-2
eBook Packages: Computer ScienceComputer Science (R0)