arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.08976cs.IR
收藏

通过保形预测实现序列推荐系统的置信度感知微调

Confidence-aware Fine-tuning of Sequential Recommendation Systems via Conformal Prediction

Chen Wang, Fangxin Wang, Ruocheng Guo, Yueqing Liang, Philip S. Yu

AI总结:

本文提出CPFT微调框架,将基于保形预测的损失与交叉熵损失结合,使序列推荐在保持top-K精确率的同时获得具备覆盖保证的高置信度预测集。

摘要:

在序列推荐系统(SRecsys)中,依赖交叉熵(CE)损失的传统训练方法通常优先考虑准确性,却无法与用户满意度指标良好对齐。CE损失专注于最大化真实物品的置信度,而这很难在所有用户和会话中普遍实现。它还忽视了将真实物品排列在前K个位置内的实际可接受性,而这是SRecsys中的常用指标。为解决这一局限,我们提出CPFT,这是一种新颖的微调框架,将基于保形预测(CP)的损失与CE损失相结合,在优化准确性的同时优化置信度,从而更好地与广泛使用的top-K指标对齐。CPFT利用可微代理损失和计算高效的校准策略,将CP原则嵌入训练循环,能够生成高置信度预测集。这些预测集聚焦于高相关性物品,同时保持稳健的覆盖保证。在五个真实世界数据集和四种不同序列模型上的大量实验表明,CPFT改善了精确率指标和置信度校准。我们的结果强调了置信度感知微调对于提供准确、可信并提升用户满意度的推荐的重要性。

英文摘要:

In Sequential Recommendation Systems (SRecsys), traditional training approaches that rely on Cross-Entropy (CE) loss often prioritize accuracy but fail to align well with user satisfaction metrics. CE loss focuses on maximizing the confidence of the ground truth item, which is challenging to achieve universally across all users and sessions. It also overlooks the practical acceptability of ranking the ground truth item within the top-$K$ positions, a common metric in SRecsys. To address this limitation, we propose \textbf{CPFT}, a novel fine-tuning framework that integrates Conformal Prediction (CP)-based losses with CE loss to optimize accuracy alongside confidence that better aligns with widely used top-$K$ metrics. CPFT embeds CP principles into the training loop using differentiable proxy losses and computationally efficient calibration strategies, enabling the generation of high-confidence prediction sets. These sets focus on items with high relevance while maintaining robust coverage guarantees. Extensive experiments on five real-world datasets and four distinct sequential models demonstrate that CPFT improves precision metrics and confidence calibration. Our results highlight the importance of confidence-aware fine-tuning in delivering accurate, trustworthy recommendations that enhance user satisfaction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑