Unlocking the Hidden Treasures: Enhancing Recommendations with Unlabeled Data

TL;DR

This paper introduces a positive-neutral-negative learning paradigm for collaborative filtering recommender systems, effectively leveraging unlabeled data through a novel semi-supervised approach and set-level ranking loss to improve recommendation accuracy.

Contribution

The paper proposes the PNN paradigm with a neutral class and a new loss function, addressing the challenge of utilizing unlabeled data in recommendation systems.

Findings

PNN significantly improves collaborative filtering performance.

Even simple matrix factorization benefits from PNN to match complex models.

The approach is validated on four real-world datasets.

Abstract

Collaborative filtering (CF) stands as a cornerstone in recommender systems, yet effectively leveraging the massive unlabeled data presents a significant challenge. Current research focuses on addressing the challenge of unlabeled data by extracting a subset that closely approximates negative samples. Regrettably, the remaining data are overlooked, failing to fully integrate this valuable information into the construction of user preferences. To address this gap, we introduce a novel positive-neutral-negative (PNN) learning paradigm. PNN introduces a neutral class, encompassing intricate items that are challenging to categorize directly as positive or negative samples. By training a model based on this triple-wise partial ranking, PNN offers a promising solution to learning complex user preferences. Through theoretical analysis, we connect PNN to one-way partial AUC (OPAUC) to validate its efficacy. Implementing the PNN paradigm is, however, technically challenging because: (1) it is difficult to classify unlabeled data into neutral or negative in the absence of supervised signals; (2) there does not exist any loss function that can handle set-level triple-wise ranking relationships. To address these challenges, we propose a semi-supervised learning method coupled with a user-aware attention model for knowledge acquisition and classification refinement. Additionally, a novel loss function with a two-step centroid ranking approach enables handling set-level rankings. Extensive experiments on four real-world datasets demonstrate that, when combined with PNN, a wide range of representative CF models can consistently and significantly boost their performance. Even with a simple matrix factorization, PNN can achieve comparable performance to sophisticated graph neutral networks.