Learnable Model Augmentation Self-Supervised Learning for Sequential Recommendation
This work addresses a domain-specific problem for sequential recommendation systems, offering an incremental improvement over existing self-supervised learning methods.
The paper tackles the problem of uniform data augmentation losing sequence correlation in self-supervised learning for sequential recommendation by proposing LMA4Rec, which uses learnable model augmentation and Bernoulli dropout to generate contrastive views, and experiments on three datasets show it effectively improves performance compared to baselines.
Sequential Recommendation aims to predict the next item based on user behaviour. Recently, Self-Supervised Learning (SSL) has been proposed to improve recommendation performance. However, most of existing SSL methods use a uniform data augmentation scheme, which loses the sequence correlation of an original sequence. To this end, in this paper, we propose a Learnable Model Augmentation self-supervised learning for sequential Recommendation (LMA4Rec). Specifically, LMA4Rec first takes model augmentation as a supplementary method for data augmentation to generate views. Then, LMA4Rec uses learnable Bernoulli dropout to implement model augmentation learnable operations. Next, self-supervised learning is used between the contrastive views to extract self-supervised signals from an original sequence. Finally, experiments on three public datasets show that the LMA4Rec method effectively improves sequential recommendation performance compared with baseline methods.