Click-Through Rate Prediction with Multi-Modal Hypergraphs

TL;DR

This paper introduces HyperCTR, a hypergraph neural network-based model that leverages multi-modal and temporal user-item interactions to improve click-through rate prediction for micro-videos, outperforming existing methods.

Contribution

The paper proposes a novel hypergraph neural network framework that incorporates multi-modal features and temporal dynamics for enhanced CTR prediction in micro-video advertising.

Findings

HyperCTR significantly outperforms state-of-the-art methods on three datasets.

Multi-modal and temporal information improve user and item representation.

Hypergraph-based modeling captures complex user-item interactions effectively.

Abstract

Advertising is critical to many online e-commerce platforms such as e-Bay and Amazon. One of the important signals that these platforms rely upon is the click-through rate (CTR) prediction. The recent popularity of multi-modal sharing platforms such as TikTok has led to an increased interest in online micro-videos. It is, therefore, useful to consider micro-videos to help a merchant target micro-video advertising better and find users' favourites to enhance user experience. Existing works on CTR prediction largely exploit unimodal content to learn item representations. A relatively minimal effort has been made to leverage multi-modal information exchange among users and items. We propose a model to exploit the temporal user-item interactions to guide the representation learning with multi-modal features, and further predict the user click rate of the micro-video item. We design a Hypergraph Click-Through Rate prediction framework (HyperCTR) built upon the hyperedge notion of hypergraph neural networks, which can yield modal-specific representations of users and micro-videos to better capture user preferences. We construct a time-aware user-item bipartite network with multi-modal information and enrich the representation of each user and item with the generated interests-based user hypergraph and item hypergraph. Through extensive experiments on three public datasets, we demonstrate that our proposed model significantly outperforms various state-of-the-art methods.