推广正交化以适用于含非线性的模型
Generalizing Orthogonalization for Models with Non-Linearities
AI总结：
针对黑盒算法偏差问题，提出适用于ReLU等非线性的正交化与归一化方法，有效保护敏感数据并消除神经网络及嵌入中的不期望属性。
摘要：
黑盒算法的复杂性会带来诸多挑战，包括引入偏差。这些偏差在算法应用中构成了直接风险。例如，有研究表明神经网络仅凭患者的X光扫描就能推断出种族信息，这超出了医学专家的能力。如果医学专家不知道这一事实，基于该算法的自动决策可能会导致仅凭种族信息开具治疗方案。虽然当前的方法允许针对此类信息对神经网络进行“正交化”或“归一化”，但现有方法均基于线性模型。我们的论文通过引入对 ReLU 激活等非线性的修正，推进了相关研究。我们的方法还涵盖标量和张量值预测，便于将其集成到神经网络架构中。通过大量实验，我们验证了该方法在保护广义线性模型中的敏感数据、对元数据归一化卷积神经网络，以及纠正预存嵌入中不期望属性方面的有效性。
英文摘要：
The complexity of black-box algorithms can lead to various challenges, including the introduction of biases. These biases present immediate risks in the algorithms' application. It was, for instance, shown that neural networks can deduce racial information solely from a patient's X-ray scan, a task beyond the capability of medical experts. If this fact is not known to the medical expert, automatic decision-making based on this algorithm could lead to prescribing a treatment (purely) based on racial information. While current methodologies allow for the "orthogonalization" or "normalization" of neural networks with respect to such information, existing approaches are grounded in linear models. Our paper advances the discourse by introducing corrections for non-linearities such as ReLU activations. Our approach also encompasses scalar and tensor-valued predictions, facilitating its integration into neural network architectures. Through extensive experiments, we validate our method's effectiveness in safeguarding sensitive data in generalized linear models, normalizing convolutional neural networks for metadata, and rectifying pre-existing embeddings for undesired attributes.
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。
