Loading...

Recurrent poisson factorization for temporal recommendation

Hosseini, S ; Sharif University of Technology | 2018

850 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/TKDE.2018.2879796
  3. Publisher: IEEE Computer Society , 2018
  4. Abstract:
  5. Poisson Factorization (PF) is the gold standard framework for recommendation systems with implicit feedback whose variants show state-of-the-art performance on real-world recommendation tasks. However, most of the previous work do not explicitly take into account the temporal behavior of users which is essential to recommend the right item to the right user at the right time. In this paper, we introduce a Recurrent Poisson Factorization (RPF) framework that generalizes the classical PF methods by utilizing a Poisson process for modeling the implicit feedback. RPF treats time as a natural constituent of the model, and takes important factors for recommendation into consideration to provide a rich family of time-sensitive factorization models. They include capturing the consumption heterogeneity among users and items (HRPF), handling dynamic user preferences and item specification (DRPF), modeling the social-aspect of product adoption (SRPF), considering the inter-item correlations (IIRPF), and also utilizing items' metadata to better infer the correlation among engagement pattern of users with items (XIIRPF). We also develop an efficient variational algorithm for approximate posterior inference that scales up to massive datasets. We demonstrate RPF's superior performance over many state-of-the-art methods on synthetic dataset, and wide variety of large scale real-world datasets. IEEE
  6. Keywords:
  7. Correlation ; Gold ; Metadata ; Poisson Factorization ; Social network services ; Task analysis ; Temporal Recommender System ; Correlation methods ; Factorization ; History ; Inference engines ; Job analysis ; Poisson distribution ; Social aspects ; Standards ; Factorization model ; Poisson process ; Real-world datasets ; State-of-the-art methods ; State-of-the-art performance ; Variational algorithms ; Recommender systems
  8. Source: IEEE Transactions on Knowledge and Data Engineering ; 2018 ; 10414347 (ISSN)
  9. URL: https://ieeexplore.ieee.org/document/8525337