APAO: Adaptive Prefix-Aware Optimization for Generative Recommendation

TL;DR

APAO introduces a prefix-aware optimization framework for generative recommendation models, aligning training with inference to improve recommendation accuracy under beam search constraints.

Contribution

The paper proposes the APAO framework with prefix-level optimization and adaptive worst-prefix strategies to address training-inference mismatch in generative recommendation.

Findings

APAO improves recommendation performance across multiple datasets.

The framework effectively reduces training-inference inconsistency.

Experimental results show consistent gains over baseline models.

Abstract

Generative recommendation has recently emerged as a promising paradigm in sequential recommendation. It formulates the task as an autoregressive generation process, predicting discrete tokens of the next item conditioned on user interaction histories. Existing generative recommendation models are typically trained with token-level likelihood objectives, such as cross-entropy loss, while employing multi-step beam search during inference to generate ranked item candidates. However, this leads to a fundamental training-inference inconsistency: standard training assumes ground-truth history is always available, ignoring the fact that beam search prunes low-probability branches during inference. Consequently, the correct item may be prematurely discarded simply because its initial tokens (prefixes) have low scores. To address this issue, we propose the Adaptive Prefix-Aware Optimization (APAO) framework, which introduces prefix-level optimization losses to better align the training objective with the inference setting. Furthermore, we design an adaptive worst-prefix optimization strategy that dynamically focuses on the most vulnerable prefixes during training, thereby enhancing the model's ability to retain correct candidates under beam search constraints. We provide theoretical analyses to demonstrate the effectiveness and efficiency of our framework. Extensive experiments on multiple datasets further show that APAO consistently alleviates the training-inference inconsistency and improves performance across various generative recommendation backbones. Our codes are publicly available at https://github.com/yuyq18/APAO.