ContextGNN: Beyond Two-Tower Recommendation Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Yiwen, Zhang, Zecheng, He, Xinwei, Nitta, Akihiro, Hu, Weihua, Wang, Dong, Shah, Manan, Huang, Shenyang, Stojanovič, Blaž, Krumholz, Alan, Lenssen, Jan Eric, Leskovec, Jure, Fey, Matthias
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915040094846976
author Yuan, Yiwen
Zhang, Zecheng
He, Xinwei
Nitta, Akihiro
Hu, Weihua
Wang, Dong
Shah, Manan
Huang, Shenyang
Stojanovič, Blaž
Krumholz, Alan
Lenssen, Jan Eric
Leskovec, Jure
Fey, Matthias
author_facet Yuan, Yiwen
Zhang, Zecheng
He, Xinwei
Nitta, Akihiro
Hu, Weihua
Wang, Dong
Shah, Manan
Huang, Shenyang
Stojanovič, Blaž
Krumholz, Alan
Lenssen, Jan Eric
Leskovec, Jure
Fey, Matthias
contents Recommendation systems predominantly utilize two-tower architectures, which evaluate user-item rankings through the inner product of their respective embeddings. However, one key limitation of two-tower models is that they learn a pair-agnostic representation of users and items. In contrast, pair-wise representations either scale poorly due to their quadratic complexity or are too restrictive on the candidate pairs to rank. To address these issues, we introduce Context-based Graph Neural Networks (ContextGNNs), a novel deep learning architecture for link prediction in recommendation systems. The method employs a pair-wise representation technique for familiar items situated within a user's local subgraph, while leveraging two-tower representations to facilitate the recommendation of exploratory items. A final network then predicts how to fuse both pair-wise and two-tower recommendations into a single ranking of items. We demonstrate that ContextGNN is able to adapt to different data characteristics and outperforms existing methods, both traditional and GNN-based, on a diverse set of practical recommendation tasks, improving performance by 20% on average.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19513
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ContextGNN: Beyond Two-Tower Recommendation Systems
Yuan, Yiwen
Zhang, Zecheng
He, Xinwei
Nitta, Akihiro
Hu, Weihua
Wang, Dong
Shah, Manan
Huang, Shenyang
Stojanovič, Blaž
Krumholz, Alan
Lenssen, Jan Eric
Leskovec, Jure
Fey, Matthias
Information Retrieval
Machine Learning
Recommendation systems predominantly utilize two-tower architectures, which evaluate user-item rankings through the inner product of their respective embeddings. However, one key limitation of two-tower models is that they learn a pair-agnostic representation of users and items. In contrast, pair-wise representations either scale poorly due to their quadratic complexity or are too restrictive on the candidate pairs to rank. To address these issues, we introduce Context-based Graph Neural Networks (ContextGNNs), a novel deep learning architecture for link prediction in recommendation systems. The method employs a pair-wise representation technique for familiar items situated within a user's local subgraph, while leveraging two-tower representations to facilitate the recommendation of exploratory items. A final network then predicts how to fuse both pair-wise and two-tower recommendations into a single ranking of items. We demonstrate that ContextGNN is able to adapt to different data characteristics and outperforms existing methods, both traditional and GNN-based, on a diverse set of practical recommendation tasks, improving performance by 20% on average.
title ContextGNN: Beyond Two-Tower Recommendation Systems
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2411.19513