Sequential Recommendation with Bidirectional Chronological Augmentation of Transformer

Sequential recommendation can capture user chronological preferences from their historical behaviors, yet the learning of short sequences (cold start problem) is still an open challenge. Recently, data augmentation with pseudo-prior items generated by transformers has drawn considerable attention. These methods can generate pseudo-prior items sequentially in reverse chronological order to extend the training sequence. However, the performance may still degrade in very short sequences; most notably, the generation of pseudo-prior items does not take into account the forward direction (from the past to the future), and so the underlying temporal correlations are not preserved in terms of conditional probabilities. Motivated by this, we propose a Bidirectional Chronological Augmentation of Transformer (BiCAT) that uses a forward learning constraint in the reverse generative process to capture contextual information more effectively. Such self-knowledge distillation can bridge the gap between data augmentation and model representation, which enhances the robustness of sequence encoder. Moreover, an informative positive and negative sampling strategy is proposed to accelerate optimization and prevent overfitting. Extensive experiments on two popular real-world datasets demonstrate the efficacy of our method: on very short sequences and long sequences, our approach can improve state-of-the-art performance by an average of 35.04% and 8.76% respectively, in terms of Recall@5.