Efficient Neural Interaction Function Search for Collaborative Filtering

Abstract

In collaborative filtering (CF), interaction function (IFC) plays the important role of capturing interactions among items and users. The most popular IFC is the inner product, which has been successfully used in low-rank matrix factorization. However, interactions in real-world applications can be highly complex. Thus, other operations (such as plus and concatenation), which may potentially offer better performance, have been proposed. Nevertheless, it is still hard for existing IFCs to have consistently good performance across different application scenarios. Motivated by the recent success of automated machine learning (AutoML), we propose in this paper the search for simple neural interaction functions (SIF) in CF. By examining and generalizing existing CF approaches, an expressive SIF search space is designed and represented as a structured multi-layer perceptron. We propose an one-shot search algorithm that simultaneously updates both the architecture and learning parameters. Experimental results demonstrate that the proposed method can be much more efficient than popular AutoML approaches, can obtain much better prediction performance than state-of-the-art CF approaches, and can discover distinct IFCs for different data sets and tasks

arXiv commentAccepted to WWW 2020

References in corpus (7)

• Continuous control with deep reinforcement learning
• Neural Architecture Search with Reinforcement Learning
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• DARTS: Differentiable Architecture Search
• Designing Neural Network Architectures using Reinforcement Learning
• Higher-Order Factorization Machines
• Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly