Abstract
Model calibration and debiasing are fundamental to the reliability and fairness of large scale recommendation systems. We introduce the Isotonic Layer, a novel, differentiable framework that integrates piecewise linear fitting directly into neural architectures. By partitioning the feature space into discrete segments and optimizing non negative slopes via a constrained dot product mechanism, we enforce a global monotonic inductive bias. This ensures model outputs remain logically consistent with critical features such as latent relevance, recency, or quality scores. We further generalize this architecture by parameterizing segment wise slopes as learnable embeddings. This enables the model to adaptively capture context specific distortions, such as position based CTR bias through specialized isotonic profiles. Our approach utilizes a dual task formulation that decouples the recommendation objective into latent relevance estimation and bias aware calibration. A major contribution of this work is the ability to perform highly granular, customized calibration for arbitrary combinations of context features, a level of control difficult to achieve with traditional non parametric methods. We also extend this to Multi Task Learning environments with dedicated embeddings for distinct objectives. Extensive empirical evaluations on real world datasets and production AB tests demonstrate that the Isotonic Layer effectively mitigates systematic bias and enhances calibration fidelity, significantly outperforming production baselines in both predictive accuracy and ranking consistency.
Abstract (translated)
模型校准和去偏是大规模推荐系统可靠性和公平性的基础。我们引入了Isotonic层，这是一种新颖的、可微分框架，它将分段线性拟合直接集成到神经架构中。通过划分特征空间为离散片段，并通过约束点积机制优化非负斜率，我们强制执行全局单调归纳偏置。这确保模型输出在与潜在相关性、最近性和质量评分等关键特征逻辑一致方面保持一致性。 我们将此架构进一步推广，将分段斜率参数化为可学习嵌入。这种方法使模型能够自适应地捕获上下文特异性失真，例如通过专门的Isotonic配置文件来捕获基于位置的点击率偏差。我们的方法利用了双任务公式，该公式将推荐目标解耦为潜在相关性估计和感知偏见校准。这项工作的主要贡献之一是可以针对任意组合的上下文特征执行高度精细化、定制化的校准，这是传统非参数方法难以实现的控制级别。 我们还将这种方法扩展到多任务学习环境中，使用专用嵌入来处理不同的目标。在真实世界数据集和生产A/B测试中的广泛实证评估表明，Isotonic层有效地减轻了系统偏差，并提高了校准保真度，在预测准确性和排名一致性方面显著优于现有的基准模型。
URL
https://arxiv.org/abs/2603.06589
