发表机构
Huazhong University of Science and Technology（华中科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对神经网络合并数据时可能出现的偏好反转问题，推导了相关保留条件，提出了Gram不匹配度量与正则化方法，开发了三阶段审计流程，使组合可靠性可测量可操作。
AI 中文摘要
神经网络越来越多地结合不同群体、时间段和运行条件的数据来提升泛化能力，这引发了一个可靠性问题：在合并数据上重新拟合的模型是否能保留两个数据源共同支持的行动排序。案例式决策理论（CBDT）通过其组合公理将这一要求形式化，该公理要求数据源支持的偏好在其并集中得以保留。我们研究了固定表示的神经网络结合普通最小二乘（OLS）输出头时，该属性何时成立。首先，我们证明合并重新拟合会重新计算用于加权数据源证据的逆Gram几何，这可能反转共享偏好，并推导了精确和近似的保留条件。接下来，我们引入一种尺度不变的Gram不匹配度量，用于对候选池进行优先级排序，以及一种面向几何的正则化方法，用于在训练期间塑造源几何。最后，我们开发了一个三阶段审计流程，通过决策变化追踪任务定义的效用损失的严格成对反转。在基于负载的投标代理以及医疗和金融决策代理上的实验揭示了稳定和易发生反转的合并机制：负载审计在代理效用下识别出可测量的非零类源共识相关有害决策，而跨域审计显示，相当的不匹配可能对应截然不同的保留率。面向几何的目标占据了不同的描述准确性-一致性-几何-有害性操作点。总体而言，该框架通过筛选、分析认证、面向几何的训练和决策后果审计，使组合可靠性可测量且可操作。
英文摘要
Neural networks increasingly combine data across populations, time periods, and operating conditions to improve generalization. This raises a reliability question: whether a model refitted on pooled data preserves an action ordering supported by both sources. Case-Based Decision Theory (CBDT) formalizes this requirement through its composition axiom, which requires source-supported preferences to survive their union. We study when this property holds for fixed-representation neural networks with ordinary least squares (OLS) output heads. First, we show that pooled refitting recomputes the inverse-Gram geometry used to weight source evidence, which can reverse shared preferences, and derive exact and approximate preservation conditions. Next, we introduce a scale-invariant Gram mismatch measure for prioritizing candidate pools and geometry-oriented regularization for shaping source geometry during training. Finally, we develop a three-stage audit that traces strict pairwise reversals through decision changes to task-defined utility loss. Experiments spanning a load-based bidding proxy and medical and financial decision proxies reveal stable and reversal-prone pooling regimes: the load audit identifies a measurable nonzero class of source-consensus-relative harmful decisions under the proxy utility, while cross-domain audits show that comparable mismatch can correspond to sharply different preservation rates. Geometry-oriented objectives occupy distinct descriptive accuracy-consistency-geometry-harm operating points. Together, the framework makes compositional reliability measurable and operational through screening, analytic certification, geometry-oriented training, and decision-consequence auditing.
Comments15 pages
