MIMA：基于多正例互斥分配的多兴趣推荐
MIMA: Multi-Interest Recommendation via Multi-Positive Exclusive Assignment
- Alibaba International Digital Commerce Group（阿里巴巴国际数字商业集团）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对多兴趣推荐中的兴趣坍缩问题，提出MIMA框架，通过多正例互斥分配和因果Transformer生成互补兴趣，并利用路由模块校准得分，在公共和工业数据集上超越现有方法。
AI中文摘要：
多兴趣推荐使用多个兴趣向量来表示每个用户，以实现细粒度的候选匹配，但该方法常常遭受兴趣坍缩问题，即学习到的兴趣收敛为相似的表示。我们强调，普遍存在的单正例范式是导致该问题的一个重要因素。由于每个实例仅提供一个正例物品，各个意图被独立优化，这可能导致同一个最佳匹配兴趣被反复更新以适配不同的正例，而其他兴趣则缺乏监督。此外，现有方法很少建模用户对每个兴趣的激活强度，导致推理时不同兴趣通道的得分无法比较。为解决这些问题，我们提出了MIMA，一种基于多正例互斥分配的多兴趣推荐框架。MIMA将同一请求内共同出现的物品分组为正例集合，使用因果Transformer解码器生成互补的兴趣，并通过匈牙利匹配将每个正例互斥地分配给一个不同的兴趣进行监督，从而使兴趣差异化源于训练目标本身，而非辅助正则化。一个轻量级路由模块进一步估计用户兴趣激活概率，以校准跨兴趣通道的得分。在三个公共数据集和一个工业数据集上的实验表明，MIMA持续优于最先进的基线方法，在线A/B测试也带来了显著的商业收益。
英文摘要：
Multi-interest recommendation represents each user with multiple interest vectors for fine-grained candidate matching, yet it often suffers from interest collapse, where the learned interests converge to similar representations. We highlight the prevailing single-positive paradigm as one important factor behind this issue. Since each instance provides only one positive item, intents are optimized independently, potentially causing the same best-matching interest to be repeatedly updated toward different positives while leaving the others under-supervised. Moreover, existing methods rarely model how strongly a user activates each interest, leaving scores from different interest channels incomparable at inference. To address these problems, we propose MIMA, a Multi-Interest recommendation framework built on Multi-positive exclusive Assignment. MIMA groups items co-occurring within the same request into a positive set, generates complementary interests with a causal Transformer decoder, and exclusively assigns each positive to supervise a distinct interest via Hungarian matching, so that interest differentiation emerges from the training objective itself rather than auxiliary regularization. A lightweight routing module further estimates user-interest activation probabilities to calibrate scores across interest channels. Experiments on three public datasets and an industrial dataset show that MIMA consistently outperforms state-of-the-art baselines, and an online A/B test yields significant business gains.
