Learnable Model Augmentation Contrastive Learning for Sequential Recommendation

doi:10.1109/TKDE.2023.3330426

Learnable Model Augmentation Contrastive Learning for Sequential Recommendation

2024-08-01

0

PRE

AI

DOI：10.1109/TKDE.2023.3330426

Original

Original request for help

Save

Abstract

En 中文

Sequential Recommendation (SR) methods play a crucial role in recommender systems, which aims to capture users' dynamic interest from their historical interactions. Recently, Contrastive Learning (CL), which has emerged as a successful method for sequential recommendation, utilizes various data augmentations to generate contrastive views to mine supervised signals from data to alleviate data sparsity issues. However, most existing sequential data augmentation methods may destroy semantic sequential interaction characteristics. Meanwhile, they often adopt random operations when generating contrastive views leading to suboptimal performance. To this end, in this paper, we propose a Learnable Model Augmentation Contrastive learning for sequential Recommendation (LMA4Rec). Specifically, LMA4Rec first takes the model-based augmentation method to generate constructive views. Then, LMA4Rec uses Learnable Bernoulli Dropout (LBD) to implement learnable model augmentation operations. Next, contrastive learning is used between the contrastive views to extract supervised signals. Furthermore, a novel multi-positive contrastive learning loss alleviates the supervised sparsity issue. Finally, experiments on public datasets show that our LMA4Rec method effectively improved sequential recommendation performance compared with the state-of-the-art baseline methods.

Keywords:

Task analysis

Electronic mail

Data augmentation

Semantics

Markov processes

Data models

Neurons

Contrastive learning

learnable dropout

model augmentation

multi-positive pairs

sequential recommendation

Learnable Model Augmentation Contrastive Learning for Sequential Recommendation

Abstract

Journal

Organization