ContextGNN: Beyond Two-Tower Recommendation Systems

• URL: http://arxiv.org/abs/2411.19513v1
• Date: Fri, 29 Nov 2024 07:11:42 GMT
• Title: ContextGNN: Beyond Two-Tower Recommendation Systems
• Authors: Yiwen Yuan, Zecheng Zhang, Xinwei He, Akihiro Nitta, Weihua Hu, Dong Wang, Manan Shah, Shenyang Huang, Blaž Stojanovič, Alan Krumholz, Jan Eric Lenssen, Jure Leskovec, Matthias Fey,
• Abstract summary: We introduce Context-based Graph Neural Networks (ContextGNNs) for link prediction in recommendation systems. The method employs a pair-wise representation technique for familiar items situated within a user's local subgraph. A final network then predicts how to fuse both pair-wise and two-tower recommendations into a single ranking of items.
• Score: 47.50792319918014
• License:
• Abstract: 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.

Related papers

• Graph-Sequential Alignment and Uniformity: Toward Enhanced Recommendation Systems [51.716704243764994]
  Our framework uses Graph Neural Network (GNN)-based and sequential recommenders as separate submodules while sharing a unified embedding space optimized jointly. Experiments on three real-world datasets demonstrate that the proposed method significantly outperforms using either approach alone.
  arXiv  Detail & Related papers  (2024-12-05T15:59:05Z)
• CADRL: Category-aware Dual-agent Reinforcement Learning for Explainable Recommendations over Knowledge Graphs [34.83895369861899]
  We propose a category-aware dual-agent reinforcement learning model for explainable recommendations over knowledge graphs. Our model comprises two components: (1) a category-aware gated graph neural network that jointly captures context-aware item representations from neighboring entities and categories, and (2) a dual-agent RL framework where two agents efficiently traverse long paths to search for suitable items.
  arXiv  Detail & Related papers  (2024-08-06T13:07:08Z)
• Dual Policy Learning for Aggregation Optimization in Graph Neural Network-based Recommender Systems [4.026354668375411]
  We propose a novel reinforcement learning-based message passing framework for recommender systems. This framework adaptively determines high-order connectivity to aggregate users and items using dual policy learning. Our results show that our proposed framework significantly enhances the recent base model, improving nDCG and Recall by up to 63.7% and 42.9%, respectively.
  arXiv  Detail & Related papers  (2023-02-21T09:47:27Z)
• IA-GCN: Interactive Graph Convolutional Network for Recommendation [13.207235494649343]
  Graph Convolutional Network (GCN) has become a novel state-of-the-art for Collaborative Filtering (CF) based Recommender Systems (RS) We build bilateral interactive guidance between each user-item pair and propose a new model named IA-GCN (short for InterActive GCN) Our model is built on top of LightGCN, a state-of-the-art GCN model for CF, and can be combined with various GCN-based CF architectures in an end-to-end fashion.
  arXiv  Detail & Related papers  (2022-04-08T03:38:09Z)
• A cross-domain recommender system using deep coupled autoencoders [77.86290991564829]
  Two novel coupled autoencoder-based deep learning methods are proposed for cross-domain recommendation. The first method aims to simultaneously learn a pair of autoencoders in order to reveal the intrinsic representations of the items in the source and target domains. The second method is derived based on a new joint regularized optimization problem, which employs two autoencoders to generate in a deep and non-linear manner the user and item-latent factors.
  arXiv  Detail & Related papers  (2021-12-08T15:14:26Z)
• SiReN: Sign-Aware Recommendation Using Graph Neural Networks [6.739000442575012]
  We present SiReN, a new sign-aware recommender system based on GNN models. SiReN consistently outperforms state-of-the-art NE-aided recommendation methods.
  arXiv  Detail & Related papers  (2021-08-19T15:07:06Z)
• A Survey on Neural Recommendation: From Collaborative Filtering to Content and Context Enriched Recommendation [70.69134448863483]
  Research in recommendation has shifted to inventing new recommender models based on neural networks. In recent years, we have witnessed significant progress in developing neural recommender models.
  arXiv  Detail & Related papers  (2021-04-27T08:03:52Z)
• Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations [85.6250759280292]
  Cross domain recommender systems have been increasingly valuable for helping consumers identify useful items in different applications. Existing cross-domain models typically require large number of overlap users, which can be difficult to obtain in some applications. We propose a novel cross-domain recommendation model based on dual learning that transfers information between two related domains in an iterative manner.
  arXiv  Detail & Related papers  (2021-04-17T09:18:59Z)
• Joint Item Recommendation and Attribute Inference: An Adaptive Graph Convolutional Network Approach [61.2786065744784]
  In recommender systems, users and items are associated with attributes, and users show preferences to items. As annotating user (item) attributes is a labor intensive task, the attribute values are often incomplete with many missing attribute values. We propose an Adaptive Graph Convolutional Network (AGCN) approach for joint item recommendation and attribute inference.
  arXiv  Detail & Related papers  (2020-05-25T10:50:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.