Data Science Lab

Introduction

With the renaissance of new-generation artificial intelligence (AI) and deep neural networks and the era of data science, and the fusion of various analytical, interaction and intelligent technologies and systems including statistical learning, mathematical modeling, natural language processing (NLP), computer vision (CV), and game playing with recommender systems, recommendation and recommender systems have become probably one of the most popular AI area, deeply integrating into every part of our daily life, working, studying, entertaining, economy, and society.

Classic RSs take the assumption that the relevant recommendation problems and data, e.g. ratings, contents and social relations, are independent and identical distributed (IID) [4,5], which is inconsistent with real-life data characteristics and problem complexities. Recommender systems must be non-IID to cope with heterogeneities and coupling relationships [2,3,5] in the problem, system, behavior, and data. In addition, the state-of-the-art machine learning approaches including deep learning and data-driven discovery and learning and their applications have become the primary engine to develop advanced RSs.

Research Topics

Modeling psychological intent and attraction: modeling human psychological intent, belief, preference, sentiment and emotion and product attraction and competitiveness that drive consumer choices, behaviors and preferences, and product attraction and competitiveness, and rational and irrational user choices, e.g., [6-8,37];
Non-IID recommender systems: modeling the heterogeneities and couplings in products, users, contexts, sessions, behaviors, and interactions, etc. [2-5];
Cross-domain recommender systems: developing theories and systems to enable multi-domain recommendations, transfer knowledge learned in one domain to another for recommendations, etc. [20];
Group-based recommender systems: making recommendations for a group of products or users by understanding their group preferences, attractions, and contexts, etc. [39,42];
Social recommender systems: modeling social relationships between users for recommendations;
Context-aware recommender systems: modeling contextual and environmental factors surrounding recommendable products and users to enable context-based recommendations, etc. [29,30,34,36,38,47,48];
Multimodal recommender systems: modeling information and relationships in multiple modalities (e.g., textual, transactional, and visual) associated with recommendable products, users, contexts for recommendations [6,26,27];
Multi-criteria recommender systems: measuring and optimizing multiple criteria of recommendable products and users, etc.;
Sequential recommender systems: modeling sequential products and services, user behaviors and preferences, contextual dynamics for next-item, next-basket, next-action recommendations, etc. [43];
Interactive recommender systems: modeling sequential interactions between users and products, positive/negative feedbacks for sequential recommendations, etc. [49];
Personalized recommender systems: modeling user-specific, product-specific, context-specific, and scenario-specific characteristics, preferences, behaviors, contexts, etc. for tailored recommendations [31,34].

Tutorials

Shoujin Wang, Liang Hu, Yan Wang, Longbing Cao, Quan Z. Sheng, and Mehmet A. Orgun. Next-Generation Recommender Systems and Their Advanced Applications at IJCAI-PRICAI2020
Liang Hu, Shoujin Wang, Longbing Cao and Songlei Jian. Coupling Everything: A Universal Guideline for Building State-of-The-Art Recommender Systems at IJCAI2019, with Tutorial Slides
Liang Hu, Longbing Cao, Songlei Jian. Non-IID Recommender Systems in Practice with Modern AI Techniques, PAKDD2018 Tutorial Melbourne, Australia, download the (Tutorial Slides).
Liang Hu, Longbing Cao, Jian Cao, Songlei Jian. When Advanced Machine Learning Meets Intelligent Recommender Systems, AAAI2018 Tutorial , here is the tutorial introduction, download the (Tutorial Slides).

References

Books & Surveys
- [1] Kantor, P. B. (2015). Recommender systems handbook. F. Ricci, L. Rokach, & B. Shapira (Eds.). Berlin, Germany:: Springer.
- [2] Longbing Cao. Coupling Learning of Complex Interactions, Journal of Information Processing and Management, 51(2): 167-186 (2015). BibTeX
- [3] Longbing Cao. Non-IIDness Learning in Behavioral and Social Data, The Computer Journal, 57(9): 1358-1370 (2014). BibTeX
- [4] Longbing Cao. Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting. Engineering, 2: 212-224, doi:10.1016/J.ENG.2016.02.013., 2016. BibTeX.
- [5] Longbing Cao and Philip Yu. Non-IID Recommendation Theories and Systems. IEEE Intelligent Systems, 31(2), 81-84, 2016. BibTeX
General References
- Modeling Psychological Attraction and Intention
  - [6] Liang Hu, Songlei Jian, Longbing Cao, Qingkui Chen. Interpretable Recommendation via Attraction Modeling: Learning Multilevel Attractiveness over Multimodal Movie Contents, IJCAI2018. BibTeX
  - [7] Shoujin Wang, Liang Hu, Yan Wang, Quan Z. Sheng, Mehmet Orgun, Longbing Cao. Intention2Basket: A Neural Intention-driven Approach for Dynamic Next-basket Planning, IJCAI2020. BibTeX
  - [8] Shoujin Wang, Liang Hu, Yan Wang, Quan Z. Sheng, Mehmet Orgun and Longbing Cao. Intention Nets: Psychology-inspired User Choice Behavior Modeling for Next-basket Prediction, AAAI2020. BibTeX
- Recommendation Representation
  - [9] Songlei Jian, Liang Hu, Longbing Cao, and Kai Lu. Metric-based Auto-Instructor for Learning Mixed Data Representation. AAAI2018. BibTeX
  - [10] Mikolov, T., Corrado, G., Chen, K., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space.
  - [11] Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Distributed Representations of Words and Phrases and their Compositionality
  - [12] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
  - [13] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
- Complementary Information in Recommender Systems
  - [14] Anderson, C. (2006). The long tail: Why the future of business is selling less of more
  - [15] Pan, W., Xiang, E. W., Liu, N. N., & Yang, Q. (2010, July). Transfer Learning in Collaborative Filtering for Sparsity Reduction. In AAAI (Vol. 10, pp. 230-235).
  - [16] Singh, A. P., & Gordon, G. J. (2008, August). Relational learning via collective matrix factorization. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 650-658). ACM.
  - [17] Marlin, B.M., Zemel, R.S., Roweis, S., and Slaney, M. Collaborative filtering and the missing at random assumption. In Proceeding 23rd Conference on Uncertainty in Artificial Intelligence, 2007.
  - [18] Hu, Y., Koren, Y., and Volinsky, C. Collaborative Filtering for Implicit Feedback Datasets. In Eighth IEEE International Conference on Data Mining, 263-272, 2008.
  - [19] Elkahky, A.M., Song, Y., and He, X. A multi-view deep learning approach for cross domain user modeling in recommendation systems. In Proceedings of the 24th International Conference on World Wide Web, 278-288, 2015.
  - [20] Kim, T., Cha, M., Kim, H., Lee, J., & Kim, J. (2017). Learning to discover cross-domain relations with generative adversarial networks. arXiv preprint arXiv:1703.05192.
  - [21] Liang Hu, Longbing Cao, Jian Cao, Zhipeng Gu, Guandong Xu, Dingyu Yang. Learning Informative Priors from Heterogeneous Domains to Improve Recommendation in Cold-Start User Domains. ACM Trans. Info Sys., 35(2):, doi>10.1145/2976737, 2016. BibTeX.
  - [22] Ma, H., Yang, H., Lyu, M. R., & King, I. (2008, October). Sorec: social recommendation using probabilistic matrix factorization. In Proceedings of the 17th ACM conference on Information and knowledge management (pp. 931-940). ACM.
  - [23] Jamali, M., & Ester, M. (2010, September). A matrix factorization technique with trust propagation for recommendation in social networks. In Proceedings of the fourth ACM conference on Recommender systems (pp. 135-142). ACM.
  - [24] Ma, H., Zhou, D., Liu, C., Lyu, M. R., & King, I. (2011, February). Recommender systems with social regularization. In Proceedings of the fourth ACM international conference on Web search and data mining (pp. 287-296). ACM.
  - [25] Wang, X., He, X., Nie, L., & Chua, T. S. (2017). Item Silk Road: Recommending Items from Information Domains to Social Users. arXiv preprint arXiv:1706.03205.
- Comprehensive Information in Recommender Systems
  - [26] Oramas, S., Nieto, O., Sordo, M., & Serra, X. (2017). A deep multimodal approach for cold-start music recommendation. arXiv preprint arXiv:1706.09739.
  - [27] Lynch, C., Aryafar, K., & Attenberg, J. (2016, August). Images don't lie: Transferring deep visual semantic features to large-scale multimodal learning to rank. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 541-548). ACM.
  - [28] Liang Hu, Longbing Cao, Jian Cao, Zhipeng Gu, Guandong Xu, Jie Wang. Improving the Quality of Recommendations for Users and Items in the Tail of Distribution. ACM Trans. Info Sys., 2017. BibTeX
- Contextual Information in Recommender Systems
  - [29] Karatzoglou, A., Amatriain, X., Baltrunas, L., & Oliver, N. (2010, September). Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering. In Proceedings of the fourth ACM conference on Recommender systems (pp. 79-86). ACM.
  - [30] Rendle, S., Gantner, Z., Freudenthaler, C., & Schmidt-Thieme, L. (2011, July). Fast context-aware recommendations with factorization machines. In Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval (pp. 635-644). ACM.
  - [31] Cheng, H. T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., … & Anil, R. (2016, September). Wide & deep learning for recommender systems. In Proceedings of the 1st Workshop on Deep Learning for Recommender Systems (pp. 7-10). ACM.
  - [31] Rendle, S., Freudenthaler, C., and Schmidt-Thieme , L. (2010, August). Factorizing Personalized Markov Chains for Next-Basket Recommendation. WWW2010.
  - [32] Hidasi, B., Karatzoglou,A., Baltrunas, L., and Tikk, D. (2016, May). Session-based Recommendations with Recurrent Neural Networks. ICLR2016.
  - [33] Gravity R, B., Quadrana, M., Karatzoglou, A., and Tikk, D. (2016 August). Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations. RecSys'2016.
  - [34] Liang Hu, Longbing Cao, Guandong Xu, Jian Cao, Zhiping Gu, Shoujin Wang. Diversifying Personalized Recommendation with User-session Context. IJCAI2017. BibTeX
  - [35] Shoujin Wang, Liang Hu, Longbing CaoPerceiving the Next Choice with Comprehensive Transaction Embeddings for Online Recommendation. Perceiving the Next Choice with Comprehensive Transaction Embeddings for Online Recommendation. ECML/PKDD (2) 2017: 285-302. BibTeX.
  - [36] Shoujin Wang, Liang Hu, Longbing Cao, Xiaoshui Huang, Defu Lian and Wei Liu. Attention-based Transactional Context Embedding for Next-Item Recommendation. AAAI2018. BibTeX
  - [37] Loyola, P., Liu, C., and Hirate, Y. (2017 August). Modeling User Session and Intent with an Attention-based Encoder-Decoder Architecture. RecSys'2017.
  - [38] Lu, Q., Yang, D., Chen, T., Zhang, W., & Yu, Y. (2011, October). Informative household recommendation with feature-based matrix factorization. In proceedings of the 2nd Challenge on Context-Aware Movie Recommendation (pp. 15-22). ACM.
  - [39] Liang Hu, Jian Cao, Guandong Xu, Longbing Cao, Zhiping Gu and Wei Cao. Deep Modeling of Group Preferences for Group-based Recommendation, AAAI 2014, 1861-1867. BibTeX
  - [40] Masthoff, J. (2015). Group recommender systems: aggregation, satisfaction and group attributes. In Recommender Systems Handbook (pp. 743-776). Springer US.
  - [41] Fangfang Li, Guandong Xu, Longbing Cao. Coupled Matrix Factorization within Non-IID Context, PAKDD2015, 707-719. BibTeX
  - [42] Fangfang Li, Guandong Xu, Longbing Cao, Zhendong Niu. Coupled Group-based Matrix Factorization for Recommender System, WISE 2013. BibTeX
  - [43] Shoujin Wang, Liang Hu, Yan Wang, Longbing Cao, Michael Sheng and Mehmet Orgun. Sequential Recommender Systems: Challenges, Progress and Prospects, IJCAI2019. BibTeX
  - [44] Liang Hu, Jian Cao, Guandong Xu, Jie Wang, Zhiping Gu, Longbing Cao. Cross-Domain Collaborative Filtering via Bilinear Multilevel Analysis, IJCAI2013. BibTeX
  - [45] Liang Hu, Jian Cao, Guandong Xu, Longbing Cao, Zhiping Gu, Can Zhu. Personalized recommendation via cross-domain triadic factorization, WWW 2013. BibTeX
  - [46] Songlei Jian, Liang Hu, Longbing Cao and Kai Lu. Representation Learning with Multiple Lipschitz-constrained Alignments on Partially-labeled Cross-domain Data, AAAI2020. BibTeX
  - [47] Shoujin Wang, Liang Hu, Longbing Cao, Xiaoshui Huang, Defu Lian and Wei Liu. Attention-based Transactional Context Embedding for Next-Item Recommendation. AAAI2018. BibTeX
  - [48] Liang Hu, Longbing Cao, Guandong Xu, Jian Cao, Zhiping Gu, Shoujin Wang. Diversifying Personalized Recommendation with User-session Context. IJCAI2017. BibTeX
  - [49] Shoujin Wang, Longbing Cao, Yan Wang. A Survey on Session-based Recommender Systems, https://arxiv.org/abs/1902.04864
- Sequential Recommender Systems
  - [50] Shoujin Wang, Longbing Cao, Yan Wang, Quan Z. Sheng, Mehmet Orgun, Defu Lian. A Survey on Session-based Recommender Systems, ACM Computing Surveys. BibTeX
  - [43] Shoujin Wang, Liang Hu, Yan Wang, Longbing Cao, Michael Sheng and Mehmet Orgun. Sequential Recommender Systems: Challenges, Progress and Prospects, IJCAI2019. BibTeX
  - [7] Shoujin Wang, Liang Hu, Yan Wang, Quan Z. Sheng, Mehmet Orgun, Longbing Cao. Intention2Basket: A Neural Intention-driven Approach for Dynamic Next-basket Planning, IJCAI2020. BibTeX
  - [8] Shoujin Wang, Liang Hu, Yan Wang, Quan Z. Sheng, Mehmet Orgun and Longbing Cao. Intention Nets: Psychology-inspired User Choice Behavior Modeling for Next-basket Prediction, AAAI2020. BibTeX
  - [31] Rendle, S., Freudenthaler, C., and Schmidt-Thieme , L. (2010, August). Factorizing Personalized Markov Chains for Next-Basket Recommendation. WWW2010.
  - [36] Shoujin Wang, Liang Hu, Longbing Cao, Xiaoshui Huang, Defu Lian and Wei Liu. Attention-based Transactional Context Embedding for Next-Item Recommendation. AAAI2018. BibTeX
  - [47] Shoujin Wang, Liang Hu, Longbing Cao, Xiaoshui Huang, Defu Lian and Wei Liu. Attention-based Transactional Context Embedding for Next-Item Recommendation. AAAI2018. BibTeX
- Real-world Recommender Systems
  - Netflix Tech Blog: https://medium.com/netflix-techblog