GIFT: Graph-guIded Feature Transfer for Cold-Start Video Click-Through Rate Prediction

TL;DR

GIFT is a graph-guided feature transfer system that leverages rich information from warmed-up videos to improve cold-start video CTR prediction, significantly enhancing performance on real-world e-commerce data.

Contribution

This paper introduces a novel graph-based feature transfer method for cold-start video CTR prediction, utilizing physical and semantic linkages to transfer features effectively.

Findings

Achieves a 6.82% CTR lift on Taobao homepage.

Outperforms state-of-the-art methods significantly.

Effectively leverages multi-modal video information for cold-start scenarios.

Abstract

Short video has witnessed rapid growth in the past few years in e-commerce platforms like Taobao. To ensure the freshness of the content, platforms need to release a large number of new videos every day, making conventional click-through rate (CTR) prediction methods suffer from the item cold-start problem. In this paper, we propose GIFT, an efficient Graph-guIded Feature Transfer system, to fully take advantages of the rich information of warmed-up videos to compensate for the cold-start ones. Specifically, we establish a heterogeneous graph that contains physical and semantic linkages to guide the feature transfer process from warmed-up video to cold-start videos. The physical linkages represent explicit relationships, while the semantic linkages measure the proximity of multi-modal representations of two videos. We elaborately design the feature transfer function to make aware of different types of transferred features (e.g., id representations and historical statistics) from different metapaths on the graph. We conduct extensive experiments on a large real-world dataset, and the results show that our GIFT system outperforms SOTA methods significantly and brings a 6.82% lift on CTR in the homepage of Taobao App.