Abstract
User behaviour on purchasing is always driven by complex latent factors, which are highly disentangled in the real world. Learning latent factorized representation of users can uncover user intentions behind the observed data (i.e. user-item interaction) and improve the robustness and interpretability of the recommender system. However, existing collaborative filtering methods learning disentangled representation face problems of balancing the trade-off between reconstruction quality and disentanglement. In this paper, we propose a controllable variational autoencoder framework for collaborative filtering. Specifically, we adopt a modified Proportional-Integral-Derivative (PID) control to the \(\beta \)-VAE objective to automatically tune the hyperparameter \(\beta \) using the output of Kullback-Leibler divergence as feedback. We further introduce item embeddings to guide the system to learn representation related to the real-world concepts using a factorized Gaussian distribution. Experimental results show that our model can get a crucial improvement over state-of-the-art baselines. We further evaluate our model’s effectiveness to control the trade-off between reconstruction error and disentanglement quality in the recommendation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bowman, S.R., Vilnis, L.: Generating sentences from a continuous space. arXiv preprint arXiv:1511.06349 (2015)
Burgess, C.P., Higgins, I.: Understanding disentangling in beta-VAE. arXiv preprint arXiv:1804.03599 (2018)
Chen, T.Q., Li, X., Grosse, R.B., Duvenaud, D.K.: Isolating sources of disentanglement in variational autoencoders. In: NeurIPS, pp. 2610–2620 (2018)
Dawen, L., Rahul, G.K., Matthew, D.H., Tony, J.: Variational autoencoders for collaborative filtering. In: WWW, pp. 689–698 (2018)
Francesco, L., Stefan, B., Mario, L., Sylvain, G., Bernhard, S., Olivier, B.: Challenging common assumptions in the unsupervised learning of disentangled representations. In: PMLR, pp. 4114–4124 (2019)
Graham, C.G., Stefan, F.G., Mario, E.S.: Classical PID control. Control System Design, Prentice Hall PTR (2005)
Irina, H.: Beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2017)
Jianxin, M., Chang, Z., Peng, C., Hongxia, Y., Wenwu, Z.: Learning disentangled representations for recommendation. In: NeurIPS, pp. 5712–5723 (2019)
Jianmo, N., Jiacheng, L.: Justifying recommendations using distantly-labeled reviews and fined-grained aspects. In: EMNLP, pp. 188–197 (2019)
Julian, M., Christopher, T., Qinfeng, S., Anton, V.D.H.: Image-based recommendations on styles and substitutes. In: SIGIR, pp. 43–52 (2015)
Kim, H., Mnih, A.: Disentangling by factorising. In: ICML, pp. 2654–2663 (2018)
Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations. In: ICLR (2018)
Luo, A., Zhao, P., Liu, Y.: Collaborative self-attention network for session-based recommendation. In: IJCAI, pp. 2591–2597 (2020)
Petar, V.: Graph attention networks. In: ICLR (2018)
Ruslan, S., Andriy, M., Geoffrey, E.H.: Restricted Boltzmann machines for collaborative filtering. In: ICML, pp. 791–798 (2007)
Santosh, K., Xia, N., George, K.: FISM: factored item similarity models for top-N recommender systems. In: KDD, pp. 659–667. ACM (2013)
Shao, H., Yao, S., Sun, D., Zhang, A.: ControlVAE: controllable variational autoencoder. In: ICML, pp. 8655–8664 (2020)
Suvash, S., Aditya, K.M., Scott, S., Lexing, X.: AutoRec: autoencoders meet collaborative filtering. In: WWW, pp. 111–112 (2015)
Xi, C., Yan, D., Rein, H., John, S., Ilya, S., Pieter, A.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: NeurIPS, pp. 2172–2180 (2016)
Xiaopeng, L., James, S.: Collaborative variational autoencoder for recommender systems. In: SIGKDD, pp. 305–314 (2017)
Xiang, W., Hongye, J., An, Z., Xiangnan, H., Tat, S.C.: Disentangled graph collaborative filtering. In: SIGIR, pp. 1001–1010 (2020)
Xiangnan, H., Lizi, L., Hanwang, Z., Liqiang, N., Xia, H., Tat, S.C.: Neural collaborative filtering. In: WWW, pp. 173–182 (2017)
Yao, W., Christopher, D., Alice, X.Z., Martin, E.: Collaborative denoising auto-encoders for top-N recommender systems. In: WSDM, pp. 153–162. ACM (2016)
Yehuda, K.: Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: KDD, pp. 426–434. ACM (2018)
Yehuda, K., Robert, M.B., Chris, V.: Matrix factorization techniques for recommender systems. In: IEEE Computer, pp. 30–37 (2009)
Zhang, Y., Zhu, Z., He, Y.: Content-collaborative disentanglement representation learning for enhanced recommendation. In: RecSys, pp. 43–52. ACM (2020)
Acknowledgements
This research was partially supported by NSFC (No. 61876117, 61876217, 61872258, 61728205), ESP of the State Key Laboratory of Software Development Environment, and PAPD of Jiangsu Higher Education Institutions.
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
Li, Y., Zhao, P., Wang, D., Xian, X., Liu, Y., Sheng, V.S. (2021). Learning Disentangled User Representation Based on Controllable VAE for Recommendation. In: Jensen, C.S., et al. Database Systems for Advanced Applications. DASFAA 2021. Lecture Notes in Computer Science(), vol 12683. Springer, Cham. https://doi.org/10.1007/978-3-030-73200-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-73200-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73199-1
Online ISBN: 978-3-030-73200-4
eBook Packages: Computer ScienceComputer Science (R0)