Learning Similarity Preserving Binary Codes for Recommender Systems

TL;DR

This paper introduces a novel hashing-based recommender system, CCSR, which leverages maximum a posteriori similarity for interaction modeling, outperforming traditional matrix factorization methods on multiple datasets.

Contribution

The paper proposes the Compact Cross-Similarity Recommender (CCSR), a new module that uses similarity-based interaction modeling inspired by cross-modal retrieval, with extensive analysis of binarization methods.

Findings

CCSR outperforms matrix factorization-based methods on MovieLens1M, Amazon, and Ichiba datasets.

Performance improvements of up to 15.69% in NDCG and 4.29% in Recall on MovieLens1M.

Differentiable scaled tanh binarization causes significant performance drops when outputs are forced to binary.

Abstract

Hashing-based Recommender Systems (RSs) are widely studied to provide scalable services. The existing methods for the systems combine three modules to achieve efficiency: feature extraction, interaction modeling, and binarization. In this paper, we study an unexplored module combination for the hashing-based recommender systems, namely Compact Cross-Similarity Recommender (CCSR). Inspired by cross-modal retrieval, CCSR utilizes Maximum a Posteriori similarity instead of matrix factorization and rating reconstruction to model interactions between users and items. We conducted experiments on MovieLens1M, Amazon product review, Ichiba purchase dataset and confirmed CCSR outperformed the existing matrix factorization-based methods. On the Movielens1M dataset, the absolute performance improvements are up to 15.69% in NDCG and 4.29% in Recall. In addition, we extensively studied three binarization modules: $sign$, scaled tanh, and sign-scaled tanh. The result demonstrated that although differentiable scaled tanh is popular in recent discrete feature learning literature, a huge performance drop occurs when outputs of scaled $tanh$ are forced to be binary.