通过级联排序的视角为生成推荐引入推理
Bringing Reasoning to Generative Recommendation Through the Lens of Cascaded Ranking
AI总结:
CARE通过级联推理框架提升生成推荐的多样性与效率,解决偏见放大问题。
摘要:
生成推荐(GR)已成为一种具有高FLOPS利用率的端到端方法,用于资源高效的推荐。尽管有效性,我们显示当前GR模型存在一个关键的偏见放大问题,其中在token级偏见随着token生成进程增加而加剧,最终限制了推荐的多样性并损害了用户体验。通过比较传统多阶段流程成功的关键因素,我们揭示了GR中两个放大偏见的限制:对编码历史的同质依赖,以及固定计算预算,这阻止了更深入的用户偏好理解。为了对抗偏见放大问题,GR必须1)纳入更多的异质信息,2)在每个token生成步骤中分配更多的计算资源。为此,我们提出了CARE,一个简单而有效的级联推理框架,用于去偏见的GR。为了纳入异质信息,我们引入了一种渐进的历史编码机制,该机制随着生成过程的推进逐步整合越来越细粒度的历史信息。为了分配更多计算,我们提出了一个查询锚定的推理机制,该机制通过并行推理步骤来深入理解历史信息。我们将在三个GR骨干网络上实例化CARE。在四个数据集上的实验证果显示CARE在推荐准确性、多样性、效率和有前途的可扩展性方面都优于现有方法。代码和数据集可在https://github.com/Linxyhaha/CARE上获得。
英文摘要:
Generative Recommendation (GR) has become a promising end-to-end approach with high FLOPS utilization for resource-efficient recommendation. Despite the effectiveness, we show that current GR models suffer from a critical \textbf{bias amplification} issue, where token-level bias escalates as token generation progresses, ultimately limiting the recommendation diversity and hurting the user experience. By comparing against the key factor behind the success of traditional multi-stage pipelines, we reveal two limitations in GR that can amplify the bias: homogeneous reliance on the encoded history, and fixed computational budgets that prevent deeper user preference understanding. To combat the bias amplification issue, it is crucial for GR to 1) incorporate more heterogeneous information, and 2) allocate greater computational resources at each token generation step. To this end, we propose CARE, a simple yet effective cascaded reasoning framework for debiased GR. To incorporate heterogeneous information, we introduce a progressive history encoding mechanism, which progressively incorporates increasingly fine-grained history information as the generation process advances. To allocate more computations, we propose a query-anchored reasoning mechanism, which seeks to perform a deeper understanding of historical information through parallel reasoning steps. We instantiate CARE on three GR backbones. Empirical results on four datasets show the superiority of CARE in recommendation accuracy, diversity, efficiency, and promising scalability. The codes and datasets are available at https://github.com/Linxyhaha/CARE.
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。