Hypergrah-Enhanced Dual Convolutional Network for Bundle Recommendation
Yang Li, Kangbo Liu, Yaoxin Wu, Zhaoxuan Wang, Erik Cambria, Xiaoxu Wang
TL;DR
The paper tackles bundle recommendation by addressing information loss from models that only capture pairwise interactions among users, items, and bundles. It introduces a hypergraph-enhanced dual convolutional network ($HED$) that leverages a complete hypergraph to jointly model the ternary $U$-$I$-$B$ interactions and augments user and bundle embeddings with $U$-$B$ signals. Empirical results on the Youshu and Netease datasets show $HED$ outperforms state-of-the-art baselines, reinforced by extensive ablation studies and sensitivity analyses to validate the design choices. The work advances bundle recommendation by incorporating higher-order interaction dynamics and publicly provides code and datasets to support reproducibility and practical adoption.
Abstract
Bundle recommendations strive to offer users a set of items as a package named bundle, enhancing convenience and contributing to the seller's revenue. While previous approaches have demonstrated notable performance, we argue that they may compromise the ternary relationship among users, items, and bundles. This compromise can result in information loss, ultimately impacting the overall model performance. To address this gap, we develop a unified model for bundle recommendation, termed hypergraph-enhanced dual convolutional neural network (HED). Our approach is characterized by two key aspects. Firstly, we construct a complete hypergraph to capture interaction dynamics among users, items, and bundles. Secondly, we incorporate U-B interaction information to enhance the information representation derived from users and bundle embedding vectors. Extensive experimental results on the Youshu and Netease datasets have demonstrated that HED surpasses state-of-the-art baselines, proving its effectiveness. In addition, various ablation studies and sensitivity analyses revealed the working mechanism and proved our effectiveness. Codes and datasets are available at https://github.com/AAI-Lab/HED