Revisiting SVD to generate powerful Node Embeddings for Recommendation Systems

TL;DR

This paper revisits the use of SVD for generating node embeddings in recommendation systems, extending it with higher-order neighbor information and demonstrating its competitive performance against state-of-the-art methods.

Contribution

It introduces an extension of SVD-based embeddings to include two-hop neighbors, enhancing recommendation accuracy with a simple yet effective approach.

Findings

The extended SVD method outperforms simple SVD in all tested datasets.

The proposed approach beats many state-of-the-art methods, up to 10% margin.

Matrix factorization remains a valuable baseline in deep learning-based recommendation systems.

Abstract

Graph Representation Learning (GRL) is an upcoming and promising area in recommendation systems. In this paper, we revisit the Singular Value Decomposition (SVD) of adjacency matrix for embedding generation of users and items and use a two-layer neural network on top of these embeddings to learn relevance between user-item pairs. Inspired by the success of higher-order learning in GRL, we further propose an extension of this method to include two-hop neighbors for SVD through the second order of the adjacency matrix and demonstrate improved performance compared with the simple SVD method which only uses one-hop neighbors. Empirical validation on three publicly available datasets of recommendation system demonstrates that the proposed methods, despite being simple, beat many state-of-the-art methods and for two of three datasets beats all of them up to a margin of 10%. Through our research, we want to shed light on the effectiveness of matrix factorization approaches, specifically SVD, in the deep learning era and show that these methods still contribute as important baselines in recommendation systems.