Factorization Machines for Data with Implicit Feedback
This work addresses the challenge of making Factorization Machines effective for implicit feedback in collaborative filtering, which is incremental as it builds on existing BPR and FM methods.
The paper tackles the problem of applying Factorization Machines to datasets with implicit feedback by proposing FM-Pair, which adapts them with a pairwise loss function based on BPR, and shows that it beats state-of-the-art methods like BPR-MF in most tested datasets and is more effective for ranking than standard FMs.
In this work, we propose FM-Pair, an adaptation of Factorization Machines with a pairwise loss function, making them effective for datasets with implicit feedback. The optimization model in FM-Pair is based on the BPR (Bayesian Personalized Ranking) criterion, which is a well-established pairwise optimization model. FM-Pair retains the advantages of FMs on generality, expressiveness and performance and yet it can be used for datasets with implicit feedback. We also propose how to apply FM-Pair effectively on two collaborative filtering problems, namely, context-aware recommendation and cross-domain collaborative filtering. By performing experiments on different datasets with explicit or implicit feedback we empirically show that in most of the tested datasets, FM-Pair beats state-of-the-art learning-to-rank methods such as BPR-MF (BPR with Matrix Factorization model). We also show that FM-Pair is significantly more effective for ranking, compared to the standard FMs model. Moreover, we show that FM-Pair can utilize context or cross-domain information effectively as the accuracy of recommendations would always improve with the right auxiliary features. Finally we show that FM-Pair has a linear time complexity and scales linearly by exploiting additional features.