Search papers, labs, and topics across Lattice.
This paper introduces Retrieve-then-Adapt (ReAd), a novel framework for test-time adaptation in sequential recommendation that addresses distributional divergence and parameterized constraints. ReAd retrieves collaboratively similar items to augment user interaction sequences, then refines the initial SR prediction via a fusion mechanism incorporating the augmentation embedding. Experiments on five benchmark datasets show ReAd outperforms existing sequential recommendation methods.
Forget retraining: ReAd dynamically adapts deployed sequential recommendation models to real-time preference shifts by retrieving and integrating collaborative user preference signals at test time.
The sequential recommendation (SR) task aims to predict the next item based on users'historical interaction sequences. Typically trained on historical data, SR models often struggle to adapt to real-time preference shifts during inference due to challenges posed by distributional divergence and parameterized constraints. Existing approaches to address this issue include test-time training, test-time augmentation, and retrieval-augmented fine-tuning. However, these methods either introduce significant computational overhead, rely on random augmentation strategies, or require a carefully designed two-stage training paradigm. In this paper, we argue that the key to effective test-time adaptation lies in achieving both effective augmentation and efficient adaptation. To this end, we propose Retrieve-then-Adapt (ReAd), a novel framework that dynamically adapts a deployed SR model to the test distribution through retrieved user preference signals. Specifically, given a trained SR model, ReAd first retrieves collaboratively similar items for a test user from a constructed collaborative memory database. A lightweight retrieval learning module then integrates these items into an informative augmentation embedding that captures both collaborative signals and prediction-refinement cues. Finally, the initial SR prediction is refined via a fusion mechanism that incorporates this embedding. Extensive experiments across five benchmark datasets demonstrate that ReAd consistently outperforms existing SR methods.
