研究：用稀疏自编码器从用户嵌入中恢复可解释行为模式
User Embeddings are Superpositions of Interpretable Behavioral Modes
推荐系统工程师可以看看这篇：用 SAE 把黑盒用户嵌入拆成可命名的行为模式，还能零样本圈选受众，不用改上游模型。
这篇论文提出把用户嵌入视为可解释行为模式的稀疏叠加结构。作者用稀疏字典学习方法（如稀疏自编码器 SAE）从嵌入中恢复这些模式，并可自动生成自然语言标签。在合成数据上，SAE 的模式恢复效果优于经典稀疏基线，包括在 transformer 编码的嵌入上。方法在两个真实数据集的经典与 transformer 用户嵌入上得到验证。恢复出的标签还能对从未在文本上训练过的嵌入实现零样本受众检索与刻画，且整个过程无需修改上游嵌入系统。
User Embeddings are Superpositions of Interpretable Behavioral Modes
User embeddings are central components of modern recommendation, personalization, and behavioral modeling systems. Though these embeddings can compactly encode rich behavioral information, they are inherently dense and opaque, limiting interpretability. To address this gap, we argue that user embeddings can be understood as sparse superpositions of interpretable behavioral modes. This structure is directly predicted by generative models of user behavior for linear embeddings and extends approximately to deep-learning representations by the superposition hypothesis. Superimposed modes can naturally be recovered by sparse dictionary learning methods, such as sparse autoencoders (SAEs), and recovered modes can be automatically named and queried in natural language. We validate mode recovery against known ground truth on synthetic data, where SAEs recover modes better than classical sparse baselines, including on transformer-encoded embeddings. We then apply the method to classical and transformer-based user embeddings from two real-world datasets. We also show how the corresponding natural-language labels enable zero-shot audience retrieval and characterization over embeddings never trained on text. The framework is post-hoc and model-agnostic, requiring no modification to the upstream embedding system.