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.
翻译:序列建议可以从历史行为中捕捉用户按时间顺序排列的偏好,然而,学习短顺序(冷起始问题)仍是一个尚未解决的挑战。最近,变压器产生的假主要项目的数据增加引起了相当的注意。这些方法可以产生假主要项目,顺序依倒时间顺序顺序排列,以延长培训序列。但是,这种性能仍然可能在非常短的顺序中下降;最明显的是,伪主要项目的生成没有考虑到前向(从过去到未来),因此,基本的时间相关性不能以有条件的概率来保存。为此,我们提议采用变压器双向时间顺序加时法(BICAT),在反向基因化过程中采用前向学习限制,以更有效地获取背景信息。这种自学提法可以缩小数据增加和模型代表之间的差距,从而增强序列的稳健性。此外,为了加速优化和防止过度配置。在两种流行真实世界数据组上进行的广泛实验。