A Generic Coordinate Descent Framework for Learning from Implicit Feedback
This work addresses the problem of scalability in recommender systems for practitioners, though it is incremental as it extends existing coordinate descent methods to more complex models.
The paper tackles the computational challenge of learning from implicit feedback in recommender systems by introducing a generic coordinate descent framework for complex models, showing that k-separability enables efficient optimization and applying it to state-of-the-art models like factorization machines and Tucker decomposition.
In recent years, interest in recommender research has shifted from explicit feedback towards implicit feedback data. A diversity of complex models has been proposed for a wide variety of applications. Despite this, learning from implicit feedback is still computationally challenging. So far, most work relies on stochastic gradient descent (SGD) solvers which are easy to derive, but in practice challenging to apply, especially for tasks with many items. For the simple matrix factorization model, an efficient coordinate descent (CD) solver has been previously proposed. However, efficient CD approaches have not been derived for more complex models. In this paper, we provide a new framework for deriving efficient CD algorithms for complex recommender models. We identify and introduce the property of k-separable models. We show that k-separability is a sufficient property to allow efficient optimization of implicit recommender problems with CD. We illustrate this framework on a variety of state-of-the-art models including factorization machines and Tucker decomposition. To summarize, our work provides the theory and building blocks to derive efficient implicit CD algorithms for complex recommender models.