Information-Aware Long Sequence Compression for Sequential Recommendation

초록

Sequential recommendation (SR) aims to predict a user's next interaction by modeling temporal dependencies in historical behavior sequences. However, modeling long sequences introduces two challenges: longer histories often include noisy interactions irrelevant to a user's core interests, and increasing sequence length substantially raises computational cost while often degrading prediction accuracy due to noise accumulation. We present RDSR, a Rate-Distortion-based Sequential Recommendation framework grounded in a task-oriented rate-utility view. Instead of directly modeling full-length sequences, RDSR combines fixed-capacity token selection with VIB-based latent compression to retain task-relevant information under explicit rate control. This suppresses irrelevant interactions while preserving essential preference signals, effectively reducing sequence length and computational overhead. Extensive experiments show that RDSR improves the performance-efficiency trade-off across attention-, MLP-, and SSM-based SR backbones, with performance gains depending on backbone inductive bias. Our code and supplementary material are available at https://github.com/kangvic0615/Rate-Distortion-SR © 2026 Copyright held by the owner/author(s).

키워드