Fine-tuning Partition-aware Item Similarities for Efficient and Scalable Recommendation

TL;DR

This paper introduces a partition-aware item similarity model for recommendation systems that enhances scalability and efficiency by restricting similarity modeling within graph partitions, achieving significant speed and storage improvements.

Contribution

It proposes a novel graph partitioning approach with a data augmentation strategy to improve item similarity modeling in recommendation systems, addressing scalability issues of existing methods.

Findings

Outperforms state-of-the-art GCN models with 10x speed-up.

Achieves 95% parameter storage savings in item similarity models.

Demonstrates effectiveness on 4 benchmark datasets.

Abstract

Collaborative filtering (CF) is widely searched in recommendation with various types of solutions. Recent success of Graph Convolution Networks (GCN) in CF demonstrates the effectiveness of modeling high-order relationships through graphs, while repetitive graph convolution and iterative batch optimization limit their efficiency. Instead, item similarity models attempt to construct direct relationships through efficient interaction encoding. Despite their great performance, the growing item numbers result in quadratic growth in similarity modeling process, posing critical scalability problems. In this paper, we investigate the graph sampling strategy adopted in latest GCN model for efficiency improving, and identify the potential item group structure in the sampled graph. Based on this, we propose a novel item similarity model which introduces graph partitioning to restrict the item similarity modeling within each partition. Specifically, we show that the spectral information of the original graph is well in preserving global-level information. Then, it is added to fine-tune local item similarities with a new data augmentation strategy acted as partition-aware prior knowledge, jointly to cope with the information loss brought by partitioning. Experiments carried out on 4 datasets show that the proposed model outperforms state-of-the-art GCN models with 10x speed-up and item similarity models with 95\% parameter storage savings.