Filtering with Time-frequency Analysis: An Adaptive and Lightweight Model for Sequential Recommender Systems Based on Discrete Wavelet Transform

Sheng Lu, Mingxi Ge, Jiuyi Zhang, Wanli Zhu, Guanjin Li, Fangming Gu

Abstract:

Sequential Recommender Systems (SRS) aim to model sequential behaviors of users to capture their interests which usually evolve over
time. Transformer-based SRS have achieved distinguished successes recently. However, studies reveal self-attention mechanism in Transformerbased models is essentially a low-pass filter and ignores high frequency information potentially including meaningful user interest patterns. This motivates us to seek better filtering technologies for SRS, and finally we find Discrete Wavelet Transform (DWT), a famous time-frequency analysis technique from digital signal processing field, can effectively process both low-frequency and highfrequency information. We design an adaptive time-frequency filter with DWT technique, which decomposes user interests into multiple signals with different frequency and time, and can automatically learn weights of these signals. Furthermore, we develop DWTRec, a model for sequential recommendation all based on the adaptive timefrequency filter. Thanks to fast DWT technique, DWTRec has a lower time complexity and spacecomplexity theoretically, and is Proficient in modeling long sequences. Experiments show that our
model outperforms state-of-the-art baseline models in datasets with different domains, sparsity levels and average sequence lengths. Especially, our model shows great performance increase in contrast with previous models when the sequence grows longer, which demonstrates another advantage of our model.