Towards Comprehensive User Preference Learning: Modeling user preference dynamics across networks for recommendations
Join Zoom Meeting
https://nus-sg.zoom.us/j/94695944421?pwd=YjduS2FOUEQ2L0hDS0N0WlB1eDZzdz09
Abstract:
Recommender systems (RSs) is the generic solution to the notorious information overload problem, where a digestible subset of interesting items (e.g., news, movies) are automatically identified and recommended to individual users. Personalized RSs have been successfully used in various application domains such as ecommerce, advertising, and social media. The primary goal of RSs is to accurately learn individual user preferences based on their profiles that contain information on their previous interactions. Despite the advancements and widespread application, in practice, RSs continue to suffer from incomprehensive user preference learning, owing to two primary reasons. First, the incomplete user profiles of both new and existing users lead to notorious data sparsity and cold start problems that degrade recommender performance. Second, the ever-changing nature of user preferences often makes even the most effective recommendations obsolete over time.
Nowadays, users interact with multiple social networks simultaneously, and the specialization of different social networks (e.g., Twitter for news and YouTube for entertainment related activities) enables users to maintain a multiple presence in the digital world. Therefore, the integration of user interactions from multiple social networks enables more complete user profiles containing their interests from multiple perspectives. Furthermore, in addition to the typical user-item context, incorporating temporal context enables user preference drifts on different networks to be tracked and learnt. Accordingly, in this thesis we focus on modeling user preference dynamics across multiple networks to learn comprehensive user preferences and improve the overall recommendation quality.
First, we extend the widely used Matrix Factorization (MF) model to showcase the feasibility and effectiveness of incorporating both time aware and cross-network information for the recommendation task. We further extend our solution to a novel multi-layered deep learning model to capture and integrate complex user preference drifts across networks under multiple temporal levels. Additionally, we introduce a generic listwise optimization criterion for recommendation under implicit feedback.
Second, we propose a novel multi-layered Long Short-Term Memory (LSTM) architecture for online cross-network recommendations to address the common latency issue found in practical RSs. The proposed LSTM model introduces multiple generic extensions to the vanilla LSTM model to overcome the unique challenges associated with using LSTM for the recommendation task.
Third, majority of users on a network are non-overlapped, where their accounts on other networks are unknown. Therefore, one of the major drawbacks of personalized cross-network solutions is the inability to provide recommendations to non-overlapped users. As a solution, we investigate the novel task of user preference augmentation to synthetically generate missing source network user preferences for recommendations on a target network. Accordingly, we introduce a novel Generative Adversarial Network (GAN) based multi-task learning architecture where the augmentation and recommendation tasks are learnt simultaneously.