SA-CAISR: Stage-Adaptive and Conflict-Aware Incremental Sequential Recommendation
Xiaomeng Song, Xinru Wang, Hanbing Wang, Hongyu Lu, Yu Chen, Zhaochun Ren, Zhumin Chen

TL;DR
SA-CAISR is a novel incremental sequential recommendation framework that efficiently updates models by selectively removing outdated knowledge, achieving state-of-the-art performance with minimal memory and computational costs.
Contribution
It introduces a buffer-free, stage-adaptive, conflict-aware method using Fisher-weighted knowledge screening for efficient incremental learning in SR.
Findings
Improves Recall@20 by 2.0% on average across datasets.
Reduces memory usage by 97.5%.
Reduces training time by 46.9%.
Abstract
Sequential recommendation (SR) aims to predict a user's next action by learning from their historical interaction sequences. In real-world applications, these models require periodic updates to adapt to new interactions and evolving user preferences. While incremental learning methods facilitate these updates, they face significant challenges. Replay-based approaches incur high memory and computational costs, and regularization-based methods often struggle to discard outdated or conflicting knowledge. To overcome these challenges, we propose SA-CAISR, a Stage-Adaptive and Conflict-Aware Incremental Sequential Recommendation framework. As a buffer-free framework, SA-CAISR operates using only the old model and new data, directly addressing the high costs of replay-based techniques. SA-CAISR introduces a novel Fisher-weighted knowledge-screening mechanism that dynamically identifies…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRecommender Systems and Techniques · Advanced Bandit Algorithms Research · Machine Learning in Healthcare
