Hyperbolic Hypergraphs for Sequential Recommendation

TL;DR

This paper introduces H2SeqRec, a hyperbolic hypergraph model for sequential recommendation that captures multi-scale temporal and social signals, addressing sparsity and temporal modeling limitations of existing hypergraph methods.

Contribution

The paper proposes a novel hyperbolic hypergraph architecture with pre-training and hierarchical structures for improved sequential recommendation performance.

Findings

H2SeqRec outperforms existing models on real-world datasets.

The hyperbolic space-based convolution effectively handles hypergraph sparsity.

Pre-training with self-supervised tasks enhances recommendation accuracy.

Abstract

Hypergraphs have been becoming a popular choice to model complex, non-pairwise, and higher-order interactions for recommender system. However, compared with traditional graph-based methods, the constructed hypergraphs are usually much sparser, which leads to a dilemma when balancing the benefits of hypergraphs and the modelling difficulty. Moreover, existing sequential hypergraph recommendation overlooks the temporal modelling among user relationships, which neglects rich social signals from the recommendation data. To tackle the above shortcomings of the existing hypergraph-based sequential recommendations, we propose a novel architecture named Hyperbolic Hypergraph representation learning method for Sequential Recommendation (H2SeqRec) with pre-training phase. Specifically, we design three self-supervised tasks to obtain the pre-training item embeddings to feed or fuse into the following recommendation architecture (with two ways to use the pre-trained embeddings). In the recommendation phase, we learn multi-scale item embeddings via a hierarchical structure to capture multiple time-span information. To alleviate the negative impact of sparse hypergraphs, we utilize a hyperbolic space-based hypergraph convolutional neural network to learn the dynamic item embeddings. Also, we design an item enhancement module to capture dynamic social information at each timestamp to improve effectiveness. Extensive experiments are conducted on two real-world datasets to prove the effectiveness and high performance of the model.