Abstract
Counterfactual reasoning has recently achieved impressive performance in the explainability of recommendation. However, existing counterfactual explainable methods ignore the realism of explanations and consider only the sparsity and proximity of explanations. Moreover, the huge counterfactuals space causes a time-consuming search process. In this study, we propose Prototype-Guided Counterfactual Explanations (PGCE), a novel counterfactual explainable recommendation framework to overcome the above issues. At its core, PGCE leverages a variational auto-encoder generative model to constrain the modification of features to generate counterfactual instances that are consistent with the distribution of real data. Meanwhile, we constructed a contrastive prototype for each user in a low-dimensional latent space, which can guide the search direction towards the optimal candidate instance space, thus, speed up the search process. For evaluation, we compared our method with several state-of-the-art model-intrinsic methods on three real-world datasets, in addition to the latest counterfactual reasoning-based method. Extensive experiments show that our model is not only able to efficiently generate realistic counterfactual explanations but also achieve state-of-the-art performance on other popular explainability evaluation metrics.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akula, A.R., Wang, S., Zhu, S.C.: Cocox: generating conceptual and counterfactual explanations via fault-lines. In: Proceedings of the 34rd AAAI Conference on Artificial Intelligence, pp. 2594–2601 (2020)
Alvarez-Melis, D., Jaakkola, T.S.: A causal framework for explaining the predictions of black-box sequence-to-sequence models. In: Conference on Empirical Methods in Natural Language Processing, pp. 412–421 (2017)
Chen, J., Zhuang, F., Hong, X., Ao, X., Xie, X., He, Q.: Attention-driven factor model for explainable personalized recommendation. In Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 909–912 (2018)
Chen, T., Yin, H., Ye, G., Huang, Z., Wang, Y., Wang, M.: Try this instead: personalized and interpretable substitute recommendation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 891–900 (2020)
Chen, X., et al.: Sequential recommendation with user memory networks. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 108–116 (2018)
Cheng, W., Shen, Y., Huang, L., Zhu, Y.: Incorporating interpretability into latent factor models via fast influence analysis. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 885–893 (2019)
Costa, F.S.D., Ouyang, S., Dolog, P., Lawlor, A.: Automatic generation of natural language explanations. In: Proceedings of the 23rd International Conference on Intelligent User Interfaces Companion, pp. 1–2 (2018)
Gao, C., Zheng, Y., Wang, W., Feng, F., He, X., Li, Y.: Causal inference in recommender systems: a survey and future directions. arXiv abs/2208.12397 (2022)
Ghazimatin, A., Balalau, O., Roy, R.S., Weikum, G.: Prince: provider-side interpretability with counterfactual explanations in recommender systems. In: Proceedings of the 13th International Conference on Web Search and Data Mining, pp. 196–204 (2020)
Goyal, Y., Wu, Z., Ernst, J., Batra, D., Parikh, D., Lee, S.: Counterfactual visual explanations. In: International Conference on Machine Learning, pp. 2376–2384 (2019)
Herlocker, J.L., Konstan, J.A., Riedl, J.: Explaining collaborative filtering recommendations. In: Proceedings of the 2000 ACM Conference on Computer Supported Cooperative Work, pp. 241–250 (2000)
Kaffes, V., Sacharidis, D., Giannopoulos, G.: Model-agnostic counterfactual explanations of recommendations. In: Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization, pp. 280–285 (2021)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)
Li, C., Quan, C., Peng, L., Qi, Y., Deng, Y., Wu, L.: A capsule network for recommendation and explaining what you like and dislike. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 275–284 (2019)
Li, O., Liu, H., Chen, C., Rudin, C.: Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions. In: Proceedings of the 32rd AAAI Conference on Artificial Intelligence, pp. 3530–3537 (2018)
Lipton, Z.C.: The mythos of model interpretability. Commun. ACM, 36–43 (2018)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Conference on Neural Information Processing Systems, pp. 4768–4777 (2017)
Ma, W., et al.: Jointly learning explainable rules for recommendation with knowledge graph. In Proceedings of the 28th International Conference on World Wide Web, pp. 1210–1221 (2019)
Mothilal, R.K., Sharma, A., Tan, C.: Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp. 607–617 (2020)
Ni, J., Li, J., McAuley, J.: Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 188–197 (2019)
Peake, G., Wang, J.: Explanation mining: post hoc interpretability of latent factor models for recommendation systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2060–2069 (2018)
Ribeiro, M.T., Singh, S., Guestrin, C.: “why should I trust you?”: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Sarwar, B.M., Karypis, G., Konstan, J.A., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th International Conference on World Wide Web, pp. 285–295 (2001)
Singh, J., Anand, A.: Posthoc interpretability of learning to rank models using secondary training data. arXiv abs/1806.11330 (2018)
Tan, J., Xu, S., Ge, Y., Li, Y., Chen, X., Zhang, Y.: Counterfactual explainable recommendation. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management, pp. 1784–1793 (2021)
Tran, K.H., Ghazimatin, A., Saha Roy, R.: Counterfactual explanations for neural recommenders. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1627–1631 (2021)
Van Looveren, A., Klaise, J.: Interpretable counterfactual explanations guided by prototypes. In: Machine Learning and Knowledge Discovery in Databases. Research Track: European Conference, pp. 650–665 (2021)
Wang, N., Wang, H., Jia, Y., Yin, Y.: Explainable recommendation via multi-task learning in opinionated text data. In: Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 165–174 (2018)
Wang, X., Li, Q., Yu, D., Xu, G.: Reinforced path reasoning for counterfactual explainable recommendation. arXiv abs/2207.06674 (2022)
Wu, T., Ribeiro, M.T., Heer, J., Weld, D.S.: Polyjuice: generating counterfactuals for explaining, evaluating, and improving models. In: Annual Meeting of the Association for Computational Linguistics, pp. 6707–6723 (2021)
Xu, S., et al.: Learning causal explanations for recommendation. In: CEUR Workshop Proceedings (2021)
Yang, L., Kenny, E.M., Ng, T.L.J., Yang, Y., Smyth, B., Dong, R.: Generating plausible counterfactual explanations for deep transformers in financial text classification. In: International Conference on Computational Linguistics, pp. 6150–6160 (2020)
Zhang, Y., Chen, X., et al.: Explainable recommendation: a survey and new perspectives. Found. Trends Inf. Retr. 14(1), 1–101 (2020)
Zhang, Y., Lai, G., Zhang, M., Zhang, Y., Liu, Y., Ma, S.: Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In: Proceedings of the 37th International ACM SIGIR conference on Research and development in information retrieval, pp. 83–92 (2014)
Zhang, Y., Zhang, H., Zhang, M., Liu, Y., Ma, S.: Do users rate or review?: Boost phrase-level sentiment labeling with review-level sentiment classification. In: Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1027–1030 (2014)
Zhang, Y., Xu, X., Zhou, H., Zhang, Y.: Distilling structured knowledge into embeddings for explainable and accurate recommendation. In: Proceedings of the 13th International Conference on Web Search and Data Mining, pp. 735–743 (2020)
Zhong, J., Negre, E.: Shap-enhanced counterfactual explanations for recommendations. In: Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing, pp. 1365–1372 (2022)
Zhou, Y., Wang, H., He, J., Wang, H.: From intrinsic to counterfactual: on the explainability of contextualized recommender systems. arXiv abs/2110.14844 (2021)
Acknowledgements.
This work is supported by the Project of Construction and Support for High-level Teaching Teams of Beijing Municipal Institutions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethical Statement
Firstly, the experimental data were all obtained from the publicly desensitised Amazon Review Data, and therefore did not involve the collection, processing or inference of private personal information. Secondly, there is no potential use of our research work for the police or the military. Thirdly, this paper does not contain any studies with animals performed by any of the authors. Finally, informed consent was obtained from all individual participants included in the study. All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
He, M., Wang, J., An, B., Wen, H. (2023). Prototype-Guided Counterfactual Explanations via Variational Auto-encoder for Recommendation. In: De Francisci Morales, G., Perlich, C., Ruchansky, N., Kourtellis, N., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14174. Springer, Cham. https://doi.org/10.1007/978-3-031-43427-3_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-43427-3_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43426-6
Online ISBN: 978-3-031-43427-3
eBook Packages: Computer ScienceComputer Science (R0)
