Incremental Multi-Dimensional Recommender Systems: Co-Factorization vs Tensors

Miguel Sozinho Ramalho, João Vinagre, Alípio Mário Jorge, Rafaela Bastos
Proceedings of the 2nd Workshop on Online Recommder Systems and User Modeling, PMLR 109:21-35, 2019.

Abstract

The present paper sets a milestone on incremental recommender systems approaches by comparing several state-of-the-art algorithms with two different mathematical foundations - matrix and tensor factorization. Traditional Pairwise Interaction Tensor Factorization is revisited and converted into a scalable and incremental option that yields the best predictive power. A novel tensor inspired approach is described. Finally, experiments compare contextless vs context-aware scenarios, the impact of noise on the algorithms, discrepancies between time complexity and execution times, and are run on five different datasets from three different recommendation areas - music, gross retail and garment. Relevant conclusions are drawn that aim to help choosing the most appropriate algorithm to use when faced with a novel recommender tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v109-ramalho19a, title = {Incremental Multi-Dimensional Recommender Systems: Co-Factorization vs Tensors}, author = {Ramalho, Miguel Sozinho and Vinagre, Jo\~{a}o and Jorge, Al\'{i}pio M\'{a}rio and Bastos, Rafaela}, booktitle = {Proceedings of the 2nd Workshop on Online Recommder Systems and User Modeling}, pages = {21--35}, year = {2019}, editor = {Vinagre, João and Jorge, Alípio Mário and Bifet, Albert and Al-Ghossein, Marie}, volume = {109}, series = {Proceedings of Machine Learning Research}, month = {19 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v109/ramalho19a/ramalho19a.pdf}, url = {https://proceedings.mlr.press/v109/ramalho19a.html}, abstract = {The present paper sets a milestone on incremental recommender systems approaches by comparing several state-of-the-art algorithms with two different mathematical foundations - matrix and tensor factorization. Traditional Pairwise Interaction Tensor Factorization is revisited and converted into a scalable and incremental option that yields the best predictive power. A novel tensor inspired approach is described. Finally, experiments compare contextless vs context-aware scenarios, the impact of noise on the algorithms, discrepancies between time complexity and execution times, and are run on five different datasets from three different recommendation areas - music, gross retail and garment. Relevant conclusions are drawn that aim to help choosing the most appropriate algorithm to use when faced with a novel recommender tasks.} }
Endnote
%0 Conference Paper %T Incremental Multi-Dimensional Recommender Systems: Co-Factorization vs Tensors %A Miguel Sozinho Ramalho %A João Vinagre %A Alípio Mário Jorge %A Rafaela Bastos %B Proceedings of the 2nd Workshop on Online Recommder Systems and User Modeling %C Proceedings of Machine Learning Research %D 2019 %E João Vinagre %E Alípio Mário Jorge %E Albert Bifet %E Marie Al-Ghossein %F pmlr-v109-ramalho19a %I PMLR %P 21--35 %U https://proceedings.mlr.press/v109/ramalho19a.html %V 109 %X The present paper sets a milestone on incremental recommender systems approaches by comparing several state-of-the-art algorithms with two different mathematical foundations - matrix and tensor factorization. Traditional Pairwise Interaction Tensor Factorization is revisited and converted into a scalable and incremental option that yields the best predictive power. A novel tensor inspired approach is described. Finally, experiments compare contextless vs context-aware scenarios, the impact of noise on the algorithms, discrepancies between time complexity and execution times, and are run on five different datasets from three different recommendation areas - music, gross retail and garment. Relevant conclusions are drawn that aim to help choosing the most appropriate algorithm to use when faced with a novel recommender tasks.
APA
Ramalho, M.S., Vinagre, J., Jorge, A.M. & Bastos, R.. (2019). Incremental Multi-Dimensional Recommender Systems: Co-Factorization vs Tensors. Proceedings of the 2nd Workshop on Online Recommder Systems and User Modeling, in Proceedings of Machine Learning Research 109:21-35 Available from https://proceedings.mlr.press/v109/ramalho19a.html.

Related Material