Filter-enhanced MLP is All You Need for Sequential Recommendation

MLP с усилением фильтрацией — всё, что нужно для последовательной рекомендации
Kun Zhou, Hui Yu, Wayne Xin Zhao, Ji–Rong Wen
2022-04-25

FMLP-Recall-MLP architecturefrequency-domain filteringlearnable filterssequential recommendation
Recently, deep neural networks such as RNN, CNN and Transformer have been applied in the task of sequential recommendation, which aims to capture the dynamic preference characteristics from logged user behavior data for accurate recommendation. However, in online platforms, logged user behavior data is inevitable to contain noise, and deep recommendation models are easy to overfit on these logged data. To tackle this problem, we borrow the idea of filtering algorithms from signal processing that attenuates the noise in the frequency domain. In our empirical experiments, we find that filtering algorithms can substantially improve representative sequential recommendation models, and integrating simple filtering algorithms (e.g., Band-Stop Filter) with an all-MLP architecture can even outperform competitive Transformer-based models. Motivated by it, we propose FMLP-Rec, an all-MLP model with learnable filters for sequential recommendation task. The all-MLP architecture endows our model with lower time complexity, and the learnable filters can adaptively attenuate the noise information in the frequency domain. Extensive experiments conducted on eight real-world datasets demonstrate the superiority of our proposed method over competitive RNN, CNN, GNN and Transformer-based methods. Our code and data are publicly available at the link: https://github.com/RUCAIBox/FMLP-Rec .
1
Combining simple filters, such as a Band-Stop Filter, with an all-MLP architecture can outperform competitive Transformer-based sequential recommendation models.
2
Experiments on eight real-world datasets demonstrate that FMLP-Rec outperforms competitive RNN-, CNN-, GNN-, and Transformer-based methods.
3
FMLP-Rec introduces learnable frequency-domain filters that adaptively suppress noise in user behavior sequences.
4
Filtering algorithms substantially improve representative sequential recommendation models by attenuating noise in the frequency domain.
5
The all-MLP design provides lower time complexity than architectures based on recurrent, convolutional, graph, or Transformer networks.

logged user behavior sequences in online platforms for sequential recommendation

dynamic user-preference modeling and noise attenuation in the frequency domain for accurate sequential recommendation

Publication Details
Publication Date
2022-04-25
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Kun Zhou
Hui Yu
Wayne Xin Zhao
Ji–Rong Wen
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%