Eicient Non-Sampling Factorization Machines for Optimal Context-Aware Recommendation

To provide more accurate recommendation, it is a trending topic to go beyond modeling user-item interactions and take context features into account. Factorization Machines (FM) with negative sampling is a popular solution for context-aware recommendation. However, it is not robust as sampling may lost important information and usually leads to non-optimal performances in practical. Several recent e orts have enhanced FM with deep learning architectures for modelling high-order feature interactions. While they either focus on rating prediction task only, or typically adopt the negative sampling strategy for optimizing the ranking performance. Due to the dramatic uctuation of sampling, it is reasonable to argue that these sampling-based FM methods are still suboptimal for context-aware recommendation. In this paper, we propose to learn FM without sampling for ranking tasks that helps context-aware recommendation particularly. Despite e ectiveness, such a non-sampling strategy presents strong challenge in learning e ciency of the model. Accordingly, we further design a new ideal framework named E cient Non-Sampling Factorization Machines (ENSFM). ENSFM not only seamlessly connects the relationship between FM and Matrix Factorization (MF), but also resolves the challenging e ciency issue via novel memorization strategies. Through extensive experiments on three realworld public datasets, we show that 1) the proposed ENSFM consistently and signi cantly outperforms the state-of-the-art methods on context-aware Top-K recommendation, and 2) ENSFM achieves signi cant advantages in training e ciency, which makes it more applicable to real-world large-scale systems. Moreover, the empirical results indicate that a proper learning method is even more important than advanced neural network structures for Top-K recommendation task. Our implementation has been released 1 to facilitate further developments on e cient non-sampling methods