Enhancing Top-N Item Recommendations by Peer Collaboration

TL;DR

This paper introduces PCRec, a peer collaboration framework that enhances top-N item recommendation accuracy by reactivating and strengthening redundant weights in DNN models through peer-based weight transplantation, without increasing inference complexity.

Contribution

The paper proposes a novel peer collaboration method to improve DNN-based recommender models by exploiting over-parameterization, enhancing performance without extra inference cost.

Findings

PCRec outperforms baseline models on real-world datasets.

Reactivating redundant weights improves recommendation accuracy.

The method is effective across multiple recommender architectures.

Abstract

Deep neural networks (DNN) have achieved great success in the recommender systems (RS) domain. However, to achieve remarkable performance, DNN-based recommender models often require numerous parameters, which inevitably bring redundant neurons and weights, a phenomenon referred to as over-parameterization. In this paper, we plan to exploit such redundancy phenomena to improve the performance of RS. Specifically, we propose PCRec, a top-N item \underline{rec}ommendation framework that leverages collaborative training of two DNN-based recommender models with the same network structure, termed \underline{p}eer \underline{c}ollaboration. PCRec can reactivate and strengthen the unimportant (redundant) weights during training, which achieves higher prediction accuracy but maintains its original inference efficiency. To realize this, we first introduce two criteria to identify the importance of weights of a given recommender model. Then, we rejuvenate the unimportant weights by transplanting outside information (i.e., weights) from its peer network. After such an operation and retraining, the original recommender model is endowed with more representation capacity by possessing more functional model parameters. To show its generality, we instantiate PCRec by using three well-known recommender models. We conduct extensive experiments on three real-world datasets, and show that PCRec yields significantly better recommendations than its counterpart with the same model (parameter) size.