Equivariant Contrastive Learning for Sequential Recommendation

TL;DR

The paper introduces ECL-SR, a novel contrastive learning framework for sequential recommendation that makes user representations sensitive or insensitive to different augmentation types, improving model discriminative power.

Contribution

It proposes an equivariant contrastive learning approach that differentiates between invasive and mild augmentations, enhancing recommendation accuracy.

Findings

ECL-SR achieves competitive performance on four benchmark datasets.

The method effectively distinguishes user behavior changes due to invasive augmentations.

ECL-SR outperforms existing models in key recommendation metrics.

Abstract

Contrastive learning (CL) benefits the training of sequential recommendation models with informative self-supervision signals. Existing solutions apply general sequential data augmentation strategies to generate positive pairs and encourage their representations to be invariant. However, due to the inherent properties of user behavior sequences, some augmentation strategies, such as item substitution, can lead to changes in user intent. Learning indiscriminately invariant representations for all augmentation strategies might be suboptimal. Therefore, we propose Equivariant Contrastive Learning for Sequential Recommendation (ECL-SR), which endows SR models with great discriminative power, making the learned user behavior representations sensitive to invasive augmentations (e.g., item substitution) and insensitive to mild augmentations (e.g., featurelevel dropout masking). In detail, we use the conditional discriminator to capture differences in behavior due to item substitution, which encourages the user behavior encoder to be equivariant to invasive augmentations. Comprehensive experiments on four benchmark datasets show that the proposed ECL-SR framework achieves competitive performance compared to state-of-the-art SR models. The source code is available at https://github.com/Tokkiu/ECL.