解决黑箱推荐系统中长尾数据提取偏差问题，提升冷门用户推荐效果。
BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation
- 通过多尺度一致性探测动态评估信号可靠性，自适应调整知识蒸馏策略。
- 在尾部用户上实现80%以上性能提升，最高超越教师模型4.98%。
- 适合需要高保真复现黑箱推荐系统的场景，尤其关注冷门商品推荐。
序列推荐系统被广泛采用，但常以黑箱API形式部署，催生了模型提取以本地复现其能力的需求。然而，长尾分布导致信号异质性：密集的头部序列使教师偏好固化，偏向局部模式；稀疏的尾部序列产生平坦且噪声大的预测。现有统一方法忽视此差异，导致噪声过拟合与知识迁移不佳。本文提出BAHSD，一种黑箱自适应蒸馏框架，通过多尺度一致性探测机制隐式量化信号可靠性。基于此，设计自适应分层目标：动态温度KL散度缓解高置信信号的偏好固化，排名一致性和InfoNCE对比学习增强低置信信号的抗噪能力。BAHSD持续优于基线，在尾部用户上实现80%以上提升，最高超越教师模型4.98%，提供即插即用的高保真黑箱推荐提取方案。
原文摘要 · Abstract (English)
Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities locally. However, the long-tail distribution induces severe signal heterogeneity: dense head sequences trigger the solidification of teacher preference, biasing extraction toward local patterns, while sparse tail sequences yield flat, noisy predictions. Existing one-size-fits-all extraction overlooks this disparity, resulting in noise overfitting and suboptimal knowledge transfer. We propose BAHSD, a black-box adaptive distillation framework that handles signal heterogeneity via a multi-scale consistency probing mechanism to implicitly quantify signal reliability. Based on this, an adaptive hierarchical objective is designed: dynamic-temperature KL divergence mitigates preference solidification for high-confidence signals, while ranking consistency and InfoNCE contrastive learning provide noise-robust enhancement for low-confidence signals. BAHSD consistently outperforms baselines, achieving up to 4.98\% gain over the teacher and 80\%+ improvement on tail users, offering a plug-and-play solution for high-fidelity black-box recommendation extraction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。