Session-based recommendations have been widely adopted for various online video and E-commerce Websites. Most existing approaches are intuitively proposed to discover underlying interests or preferences out of the anonymous session data. This apparently ignores the fact these sequential behaviors usually reflect session user's potential demand, i.e., a semantic level factor, and therefore how to estimate underlying demands from a session is challenging. To address aforementioned issue, this paper proposes a demand-aware graph neural networks (DAGNN). Particularly, a demand modeling component is designed to first extract session demand and the underlying multiple demands of each session is estimated using the global demand matrix. Then, the demand-aware graph neural network is designed to extract session demand graph to learn the demandaware item embedddings for the later recommendations. The mutual information loss is further designed to enhance the quality of the learnt embeddings. Extensive experiments are evaluated on several real-world datasets and the proposed model achieves the SOTA model performance.
Recently, reciprocal recommendation, especially for online dating applications, has attracted increasing research attention. Different from conventional recommendation problems, reciprocal recommendation aims to simultaneously best match users' mutual interests. Lots of existing methods adopt user attributes and consider the interactions between attributes to capture such interest. However, these methods failed to notice that the interactions might imply both users' preference and repulsiveness to other users, which contributes opposite to the mutual interest. Moreover, the interactions grow exponentially with user attributes, posing a great challenge for distinguishing them. To address aforementioned issues, in this paper, we propose a novel reinforced random convolutional network (RRCN) approach for reciprocal recommendation. In particular, we first separately consider the preferred and repulsive interactions, where their contributions can be modeled individually. Then, we technically propose a novel random CNN component that can randomly convolute non-adjacent features and learn representations of different interaction subsets. Furthermore, we design a reinforcement learning-based strategy to integrate with the random CNN component to select important interactions for recommendation, so that the number of attribute interactions can be reduced. We evaluate the proposed RRCN against a number of both baselines and state-of-the-art approaches on two real-world datasets, and the promising results have demonstrated the superiority of RRCN against the compared approaches in terms of a number of evaluation criteria.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.