Neural Graph Matching for Video Retrieval in Large-Scale Video-driven E-commerce

TL;DR

This paper introduces a novel bi-level Graph Matching Network (GMN) that models user-video and user-item interactions as a graph matching problem to improve video retrieval in large-scale video-driven e-commerce, demonstrating significant performance gains.

Contribution

The paper proposes a new graph matching approach with a dual graph model and bi-level matching to better understand user preferences in video-driven e-commerce.

Findings

GMN outperforms state-of-the-art methods with +1.9% AUC and +7.15% CTR improvements.

The dual graph model effectively captures user-video and user-item interactions.

Bi-level graph matching enhances user embedding quality for retrieval tasks.

Abstract

With the rapid development of the short video industry, traditional e-commerce has encountered a new paradigm, video-driven e-commerce, which leverages attractive videos for product showcases and provides both video and item services for users. Benefitting from the dynamic and visualized introduction of items,video-driven e-commerce has shown huge potential in stimulating consumer confidence and promoting sales. In this paper, we focus on the video retrieval task, facing the following challenges: (1) Howto handle the heterogeneities among users, items, and videos? (2)How to mine the complementarity between items and videos for better user understanding? In this paper, we first leverage the dual graph to model the co-existing of user-video and user-item interactions in video-driven e-commerce and innovatively reduce user preference understanding to a graph matching problem. To solve it, we further propose a novel bi-level Graph Matching Network(GMN), which mainly consists of node- and preference-level graph matching. Given a user, node-level graph matching aims to match videos and items, while preference-level graph matching aims to match multiple user preferences extracted from both videos and items. Then the proposed GMN can generate and improve user embedding by aggregating matched nodes or preferences from the dual graph in a bi-level manner. Comprehensive experiments show the superiority of the proposed GMN with significant improvements over state-of-the-art approaches (e.g., AUC+1.9% and CTR+7.15%). We have developed it on a well-known video-driven e-commerce platform, serving hundreds of millions of users every day