Multimodal Topic Learning for Video Recommendation

TL;DR

This paper introduces a multimodal topic learning approach that explicitly generates semantic video topics offline from tags, titles, and images, improving recommendation accuracy and efficiency in video streaming platforms.

Contribution

It proposes a novel multimodal topic learning algorithm that separates topic generation from recommendation, reducing online computation and enhancing recommendation quality.

Findings

The algorithm effectively generates semantic video topics offline.

Using semantic topics improves recommendation accuracy.

Reduces online computational cost significantly.

Abstract

Facilitated by deep neural networks, video recommendation systems have made significant advances. Existing video recommendation systems directly exploit features from different modalities (e.g., user personal data, user behavior data, video titles, video tags, and visual contents) to input deep neural networks, while expecting the networks to online mine user-preferred topics implicitly from these features. However, the features lacking semantic topic information limits accurate recommendation generation. In addition, feature crosses using visual content features generate high dimensionality features that heavily downgrade the online computational efficiency of networks. In this paper, we explicitly separate topic generation from recommendation generation, propose a multimodal topic learning algorithm to exploit three modalities (i.e., tags, titles, and cover images) for generating video topics offline. The topics generated by the proposed algorithm serve as semantic topic features to facilitate preference scope determination and recommendation generation. Furthermore, we use the semantic topic features instead of visual content features to effectively reduce online computational cost. Our proposed algorithm has been deployed in the Kuaibao information streaming platform. Online and offline evaluation results show that our proposed algorithm performs favorably.