Hypergraph Enhanced Knowledge Tree Prompt Learning for Next-Basket Recommendation

TL;DR

This paper introduces HEKP4NBR, a novel approach that leverages hypergraph convolution and knowledge tree prompts to improve next-basket recommendation, especially handling out-of-vocabulary items effectively.

Contribution

The paper proposes transforming knowledge graphs into prompts and employing hypergraph convolution to model complex item relationships in recommendation systems.

Findings

HEKP4NBR outperforms state-of-the-art methods on real datasets.

The hypergraph module effectively captures multi-aspect item similarities.

Prompt-based encoding improves handling of OOV items.

Abstract

Next-basket recommendation (NBR) aims to infer the items in the next basket given the corresponding basket sequence. Existing NBR methods are mainly based on either message passing in a plain graph or transition modelling in a basket sequence. However, these methods only consider point-to-point binary item relations while item dependencies in real world scenarios are often in higher order. Additionally, the importance of the same item to different users varies due to variation of user preferences, and the relations between items usually involve various aspects. As pretrained language models (PLMs) excel in multiple tasks in natural language processing (NLP) and computer vision (CV), many researchers have made great efforts in utilizing PLMs to boost recommendation. However, existing PLM-based recommendation methods degrade when encountering Out-Of-Vocabulary (OOV) items. OOV items are those whose IDs are out of PLM's vocabulary and thus unintelligible to PLM. To settle the above challenges, we propose a novel method HEKP4NBR, which transforms the knowledge graph (KG) into prompts, namely Knowledge Tree Prompt (KTP), to help PLM encode the OOV item IDs in the user's basket sequence. A hypergraph convolutional module is designed to build a hypergraph based on item similarities measured by an MoE model from multiple aspects and then employ convolution on the hypergraph to model correlations among multiple items. Extensive experiments are conducted on HEKP4NBR on two datasets based on real company data and validate its effectiveness against multiple state-of-the-art methods.