这篇论文揭示了神经网络蒸馏中一个反直觉但关键的机制——潜意识学习并不依赖初始化匹配，而是由输出头兼容性驱动。做模型压缩、知识蒸馏或研究表征对齐的研究者值得细读，它可能改变你对蒸馏数据选择的认知。
本文研究了神经网络中的“潜意识学习”现象，即学生模型通过教师模型在任务无关的输入-输出对上进行蒸馏，从而获得任务相关知识或偏差。先前研究认为这需要师生初始化高度匹配，但本文证明只需兼容的输出头即可实现。在MNIST数据集上，通过将输出分为辅助头（处理噪声）和分类头，即使在隐藏层随机初始化、增减层或改变架构（如MLP到CNN）的情况下，潜意识学习仍会发生。兼容的辅助头能传递可恢复的教师信号，使学生表征更接近教师。当分类头也兼容时，仅用噪声训练的学生模型可接近甚至匹配教师的任务性能。本文还建立了理论解释机制并推导了失效的上界，将潜意识学习从意外现象转化为可预测的机制。
Learning Through Noise: Why Subliminal Learning Works and When It Fails
In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher to student models through distillation on task-unrelated input$\unicode{x2013}$output pairs. Prior explanations tie this effect to shared or closely matched teacher$\unicode{x2013}$student initialization. We show that a closely matched initialization is not necessary. Instead, subliminal learning is governed by compatible output heads. Using a controlled MNIST setting, we split outputs into an auxiliary head (for auxiliary, task-unrelated noise signals) and a class head (for classification) to demonstrate subliminal learning occurs$\unicode{x2014}$even when we randomly initialize hidden layers and remove layers, add new layers, or change the architecture (MLP-to-CNN). Compatible auxiliary heads enable transfer of a recoverable teacher signal, bringing the student's representations closer to the teacher's. When the class heads remain compatible as well, students trained only on task-unrelated noise can approach, and in favorable regimes match, teacher-level task performance. Our setting enables us to develop a theory that explains the mechanism of subliminal learning and to derive upper bounds on when subliminal learning fails. Together, our results turn subliminal learning from a surprising transfer effect into a theoretically grounded mechanism with predictable limits.