The decoupled extended Kalman filter for dynamic exponential-family factorization models
This work addresses the need for scalable and adaptive online learning in recommender systems, though it is incremental as it adapts an existing method to a specific domain.
The paper tackled the problem of online learning for large-scale recommender systems by specializing the decoupled extended Kalman filter (DEKF) to factorization models, resulting in more flexible observations, parameter drift modeling, and uncertainty estimates, with effectiveness demonstrated through numerical experiments on synthetic and real-world data.
Motivated by the needs of online large-scale recommender systems, we specialize the decoupled extended Kalman filter (DEKF) to factorization models, including factorization machines, matrix and tensor factorization, and illustrate the effectiveness of the approach through numerical experiments on synthetic and on real-world data. Online learning of model parameters through the DEKF makes factorization models more broadly useful by (i) allowing for more flexible observations through the entire exponential family, (ii) modeling parameter drift, and (iii) producing parameter uncertainty estimates that can enable explore/exploit and other applications. We use a different parameter dynamics than the standard DEKF, allowing parameter drift while encouraging reasonable values. We also present an alternate derivation of the extended Kalman filter and DEKF that highlights the role of the Fisher information matrix in the EKF.