Generating Negative Samples for Sequential Recommendation

TL;DR

This paper introduces GenNi, a method for generating high-quality negative samples in sequential recommendation systems by leveraging the current model's learned preferences, improving training effectiveness and scalability.

Contribution

It proposes a novel negative sampling approach that dynamically generates negatives based on the current model, addressing limitations of random sampling in SR.

Findings

GenNi improves recommendation accuracy over baseline methods.

High-quality negatives enhance model training efficiency.

The method scales well to large datasets.

Abstract

To make Sequential Recommendation (SR) successful, recent works focus on designing effective sequential encoders, fusing side information, and mining extra positive self-supervision signals. The strategy of sampling negative items at each time step is less explored. Due to the dynamics of users' interests and model updates during training, considering randomly sampled items from a user's non-interacted item set as negatives can be uninformative. As a result, the model will inaccurately learn user preferences toward items. Identifying informative negatives is challenging because informative negative items are tied with both dynamically changed interests and model parameters (and sampling process should also be efficient). To this end, we propose to Generate Negative Samples (items) for SR (GenNi). A negative item is sampled at each time step based on the current SR model's learned user preferences toward items. An efficient implementation is proposed to further accelerate the generation process, making it scalable to large-scale recommendation tasks. Extensive experiments on four public datasets verify the importance of providing high-quality negative samples for SR and demonstrate the effectiveness and efficiency of GenNi.