Learning Positional Attention for Sequential Recommendation
This work addresses the need for better positional encoding in sequential recommendation systems, offering incremental improvements over existing methods.
The authors tackled the problem of improving sequential recommendation by proposing attention models that directly learn positional relations, resulting in PARec and FPARec outperforming previous self-attention-based approaches in experiments.
Self-attention-based networks have achieved remarkable performance in sequential recommendation tasks. A crucial component of these models is positional encoding. In this study, we delve into the learned positional embedding, demonstrating that it often captures the distance between tokens. Building on this insight, we introduce novel attention models that directly learn positional relations. Extensive experiments reveal that our proposed models, \textbf{PARec} and \textbf{FPARec} outperform previous self-attention-based approaches. The code can be found here: https://github.com/NetEase-Media/FPARec.