Improving One-class Recommendation with Multi-tasking on Various Preference Intensities
This work addresses the limitation in one-class recommendation systems where existing methods assume fixed preference intensities, which is incremental but improves accuracy for users and platforms relying on implicit feedback.
The paper tackles the one-class recommendation problem by proposing a multi-tasking framework that accounts for various preference intensities in implicit feedback, leading to more robust entity representations. Experimental results demonstrate that this method outperforms state-of-the-art approaches by a large margin on three large-scale real-world benchmark datasets.
In the one-class recommendation problem, it's required to make recommendations basing on users' implicit feedback, which is inferred from their action and inaction. Existing works obtain representations of users and items by encoding positive and negative interactions observed from training data. However, these efforts assume that all positive signals from implicit feedback reflect a fixed preference intensity, which is not realistic. Consequently, representations learned with these methods usually fail to capture informative entity features that reflect various preference intensities. In this paper, we propose a multi-tasking framework taking various preference intensities of each signal from implicit feedback into consideration. Representations of entities are required to satisfy the objective of each subtask simultaneously, making them more robust and generalizable. Furthermore, we incorporate attentive graph convolutional layers to explore high-order relationships in the user-item bipartite graph and dynamically capture the latent tendencies of users toward the items they interact with. Experimental results show that our method performs better than state-of-the-art methods by a large margin on three large-scale real-world benchmark datasets.