IFA:面向全生命周期行为序列建模的交互保真注意力
IFA: Interaction Fidelity Attention for Entire Lifelong Behaviour Sequence Modeling
AI总结:
针对终身行为序列采样导致信息损失的问题,提出 IFA 范式,利用 linear transformer 一次性建模候选集与完整序列,并通过目标物品关系建模和训练推理一致性损失,在快手离线与在线实验中验证了效果与效率。
摘要:
终身用户行为序列提供了丰富的用户偏好信息,并在推荐任务中取得了显著提升,但也大幅增加了计算消耗。为满足在线服务严格的延迟要求,现有方法会基于与目标物品的相似性采样一个较短的子序列。遗憾的是,不在该子序列中的物品会被丢弃,从而导致严重的信息损失。\n本文提出了一种用于对完整终身序列建模的新型高效范式,名为 Interaction Fidelity Attention(交互保真注意力,IFA)。在 IFA 中,我们将候选集中的所有目标物品一次性输入模型,并利用 linear transformer 降低候选集与序列之间交叉注意力的时间复杂度,且不会造成任何交互信息损失。我们还额外对所有目标物品之间的关系进行建模,以生成最优集合,并设计损失函数以提升训练与推理的一致性。我们通过在快手推荐系统中的离线和在线实验,证明了该模型的有效性和效率。
英文摘要:
The lifelong user behavior sequence provides abundant information of user preference and gains impressive improvement in the recommendation task, however increases computational consumption significantly. To meet the severe latency requirement in online service, a short sub-sequence is sampled based on similarity to the target item. Unfortunately, items not in the sub-sequence are abandoned, leading to serious information loss. In this paper, we propose a new efficient paradigm to model the full lifelong sequence, which is named as \textbf{I}nteraction \textbf{F}idelity \textbf{A}ttention (\textbf{IFA}). In IFA, we input all target items in the candidate set into the model at once, and leverage linear transformer to reduce the time complexity of the cross attention between the candidate set and the sequence without any interaction information loss. We also additionally model the relationship of all target items for optimal set generation, and design loss function for better consistency of training and inference. We demonstrate the effectiveness and efficiency of our model by off-line and online experiments in the recommender system of Kuaishou.
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。