ELECRec: Training Sequential Recommenders as Discriminators

TL;DR

ELECRec reframes sequential recommendation as a discrimination task, training a discriminator to distinguish real next items from sampled ones, leading to improved effectiveness and efficiency in recommendations.

Contribution

The paper introduces ELECRec, a novel approach that trains sequential recommenders as discriminators rather than generators, enhancing model performance.

Findings

Outperforms baseline methods on four datasets.

Improves training efficiency and recommendation accuracy.

Discriminator-based training yields more meaningful representations.

Abstract

Sequential recommendation is often considered as a generative task, i.e., training a sequential encoder to generate the next item of a user's interests based on her historical interacted items. Despite their prevalence, these methods usually require training with more meaningful samples to be effective, which otherwise will lead to a poorly trained model. In this work, we propose to train the sequential recommenders as discriminators rather than generators. Instead of predicting the next item, our method trains a discriminator to distinguish if a sampled item is a 'real' target item or not. A generator, as an auxiliary model, is trained jointly with the discriminator to sample plausible alternative next items and will be thrown out after training. The trained discriminator is considered as the final SR model and denoted as \modelname. Experiments conducted on four datasets demonstrate the effectiveness and efficiency of the proposed approach.