TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation
This work addresses the challenge of capturing global interactions in sequential recommendation for users, offering a novel method that reduces computation and accelerates inference.
The paper tackles the problem of sequential recommendation by proposing TV-Rec, a model that uses time-variant convolutional filters to capture position-dependent temporal variations, eliminating the need for self-attention and improving accuracy. It achieves an average performance gain of 7.49% over state-of-the-art baselines on six benchmarks.
Recently, convolutional filters have been increasingly adopted in sequential recommendation for their ability to capture local sequential patterns. However, most of these models complement convolutional filters with self-attention. This is because convolutional filters alone, generally fixed filters, struggle to capture global interactions necessary for accurate recommendation. We propose Time-Variant Convolutional Filters for Sequential Recommendation (TV-Rec), a model inspired by graph signal processing, where time-variant graph filters capture position-dependent temporal variations in user sequences. By replacing both fixed kernels and self-attention with time-variant filters, TV-Rec achieves higher expressive power and better captures complex interaction patterns in user behavior. This design not only eliminates the need for self-attention but also reduces computation while accelerating inference. Extensive experiments on six public benchmarks show that TV-Rec outperforms state-of-the-art baselines by an average of 7.49%.