Representation learning for recommender systems

• Main Author: Lucas, Vinh Tran
• Other Authors: Gao CONG
• Format: Thesis-Doctor of Philosophy
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/145694
• Institution: Nanyang Technological University

Recommender systems are widely used in many big companies such as Facebook, Google, Twitter, LinkedIn, Amazon and Netflix. They help to deal with the problem of information overload by filtering the important information fragments efficiently according to users' preferences and interests. However, it is challenging to develop highly effective models for handling various recommendation problems, from individual-level to group-level tasks. To be specific, the standard recommendation problem is personalized with respect to a single user, where it aims to identify the most interesting and relevant items to make personalized recommendation. In contrast, group level recommendation deals with groups of users instead of individuals, in which fine-grained, intricate group dynamics and preferences have to be considered. With the success of deep learning, many neural architectures have been proposed for learning-to-rank recommendation. Indeed, recent studies have shown their effectiveness and efficiency in providing better recommendations in terms of user and group-of-users satisfaction with the involvement of deep learning. The key intuition behind many successful end-to-end neural architectures for recommendation is to design appropriate frameworks that are not only able to learn rich user and item representations, but also well capture the implicit and hidden relationships behind users and items. Therefore, the objective of designing such effective neural architectures remains a challenge, especially in the context of different recommendation tasks such as general recommendation, next-item recommendation, shopping-basket recommendation, etc. This dissertation focuses on designing neural architectures for personalized and group recommendation. More specifically, we explore representation learning techniques, both Euclidean and non-Euclidean representation, for learning-to-rank user/group-of-users and item pairs. The key contributions of this dissertation are listed below. Personalized Recommendation. Our contributions are summarized as follows: - Wasserstein based Metric Learning Representation for Recommendation. We introduce a novel Wasserstein distance-based Metric Learning Chain (W-MLC) model. Our W-MLC model employs a series of metric learning, together with a Wasserstein distance to constraint on the user/item projection transformations, allowing us to encode user-item interactions better through a deeper chain. In addition, we propose a hinge loss function with personalized adaptive margins for different users. Extensive experiments on eight datasets of three different recommendation tasks reveal the effectiveness of our proposed model over eight strong state-of-the-art baselines. - Going Beyond Euclidean: Hyperbolic Representation for Recommendation. We investigate the notion of learning user and item representations in non-Euclidean space. Specifically, we study the connection between metric learning in hyperbolic space and collaborative filtering by exploring Mobius gyrovector spaces where the formalism of the spaces could be utilized to generalize the most common Euclidean vector operations. Overall, this work aims to bridge the gap between Euclidean and hyperbolic geometry in recommender systems through metric learning approach. We propose HyperML (Hyperbolic Metric Learning), a conceptually simple but highly effective model for boosting the performance. Via a series of extensive experiments, we show that our proposed HyperML not only outperforms their Euclidean counterparts, but also achieves state-of-the-art performance on multiple benchmark datasets, demonstrating the effectiveness of personalized recommendation in hyperbolic geometry. - Neural Architecture Dropout Representation for Recommendation. We introduce a new regularization effect on personalized recommendation ranking task by proposing a simple informative neural architecture to enhance the performance. Specifically, our proposed architecture, DropRec (Dropout for Recommendation), investigates the notion of adaptive architecture dropout between layers by leveraging the usage of attention mechanisms. Unlike standard approaches, we explore attention mechanisms as a method to avoid redundancy and activate only specific parts of the network for each user-item pair. In the end, we propose two variants of DropRec: Co-Attention based DropRec (C-DropRec) and Self-Attention based DropRec (S-DropRec), achieving significantly competitive performance on six widely adopted benchmark datasets over existing strong stacked multi-layered baselines, demonstrating the effectiveness of attention modules in focusing on different aspects of the architecture. - One-Off Comparison between Personalized Recommenders. We put a separate chapter in order to further introduce one additional contribution to this dissertation by proposing a one-off comparison between all the proposed architectures and baselines, across all the benchmark datasets. The datasets, evaluation protocol, metrics, and baselines will be introduced in the later section. In fact, this very extensive experiment could also be considered as a small survey of the proposed architectures on the implicit feedback problem. This chapter is designed to give the readers a general overview of the proposed representation learning techniques, as well as the performance of the well-known baselines. In addition, we also provide discussions and observations on this one-off comparison. Lastly, interesting conclusions and opinions will also be provided in this chapter. Group Recommendation. Our contributions are described as follows: - Learning Representation for Group Recommendation. We propose Medley of Sub-Attention Networks (MoSAN), a new novel neural architecture for the group recommendation task. Our proposed approach hinges upon the key intuition that the decision making process (in groups) is generally dynamic, i.e., a user's decision is highly dependent on the other group members. All in all, our key motivation manifests in a form of an attentive neural model that captures fine-grained interactions between group members. In our MoSAN model, each sub-attention module is representative of a single member, which models a user's preference with respect to all other group members. Subsequently, a Medley of Sub-Attention modules is then used to collectively make the group's final decision. Overall, our proposed model is both expressive and effective. We show that MoSAN not only achieves state-of-the-art performance but also improves standard baselines by a considerable margin.