Sequential Recommendation via Adaptive Robust Attention with Multi-dimensional Embeddings
This work addresses the need for more robust sequential recommender systems, but it appears incremental as it builds on prior multi-dimensional embedding approaches.
The paper tackled the problem of improving sequential recommendation models by enhancing robustness and generalization, resulting in a proposed model that outperforms existing self-attention architectures in experiments.
Sequential recommendation models have achieved state-of-the-art performance using self-attention mechanism. It has since been found that moving beyond only using item ID and positional embeddings leads to a significant accuracy boost when predicting the next item. In recent literature, it was reported that a multi-dimensional kernel embedding with temporal contextual kernels to capture users' diverse behavioral patterns results in a substantial performance improvement. In this study, we further improve the sequential recommender model's robustness and generalization by introducing a mix-attention mechanism with a layer-wise noise injection (LNI) regularization. We refer to our proposed model as adaptive robust sequential recommendation framework (ADRRec), and demonstrate through extensive experiments that our model outperforms existing self-attention architectures.