Neural network-based models for collaborative filtering have received widespread attention, among which variational autoencoder (VAE) has shown unique advantages in the task of item recommendation. However, most existing VAE-based models only focus on one type of user feedback, leading to their performance bottlenecks. To overcome this limitation, we propose a novel VAE-based recommendation model called VAE++, which can effectively utilize heterogeneous feedback to boost recommendation performance. Specifically, it combines three different types of signals, i.e., purchase feedback, examination feedback and their mixed feedback, via two well-designed modules, i.e., a target representation enhancement module and a target representation refinement module. The former exploits the mixed feedback to improve the learning of purchase representations, while the latter leverages the examination feedback to further refine them. In particular, purchase and examination preferences are jointly decoded in one decoder to ensure the high quality of the reconstructed samples. Extensive experiments on three public datasets show that our VAE++ achieves the best results compared with several state-of-the-art methods.

In this paper, we study a recent and important recommendation problem called heterogeneous one-class collaborative filtering (HOCCF), where we have two different types of one-class feedback, i.e., a set of browses and a set of purchases, for preference learning. Previous methods exploit the browses and purchases by extending some existing methods on modeling homogeneous one-class feedback in an integrative or sequential manner. However, an integrative method may be of high complexity in model training due to the expanded prediction rule, and a sequential method is of inconvenience in deployment because more than one parametric models have to be maintained. In this paper, we convert the HOCCF problem to an adaptive transfer learning task, where we first model browses via a factorization model from a perspective of the role of browser, and then adaptively refine the learned model parameters via purchases from a perspective of the dependent role of purchaser. Based on this conversion, we design a novel solution called role-based adaptive factorization (ROAF), and then derive two specific variants with pairwise preference learning and pointwise preference learning. Finally, we conduct extensive empirical studies on two large datasets, and find that our ROAF is a very promising solution in terms of recommendation accuracy, besides its convenience of one single parametric model in deployment.

Recommender systems play an important role in providing personalized services for users in the context of information overload. Generally, users’ feedback toward items often contain the most significant information reflecting their preferences, which enables accurate personalized recommendation. In real applications, users’ feedback are usually heterogeneous (rather than homogeneous) such as purchases and examinations in e-commerce, which reflects users’ preferences in different degrees. Effective modeling of such heterogeneous one-class feedback is challenging compared with that of homogeneous feedback of ratings. As a response, heterogeneous one-class collaborative filtering (HOCCF) is proposed, which often converts the heterogeneous feedback into two parts (i.e., target feedback and auxiliary feedback), aiming to care more about the target feedback (e.g., purchases ) with the assistance of the auxiliary feedback (e.g., examinations ). In this survey, we provide an overview of the representative HOCCF methods from the perspective of factorization-based methods, transfer learning-based methods, and deep learning-based methods. First, we review the factorization-based methods according to different strategies. Second, we describe the transfer learning-based methods with different knowledge sharing manners. Third, we discuss the deep learning-based methods according to the neural architectures. Moreover, we include some important example applications, describe the empirical studies, and discuss some promising future directions.