Hot PATE: Private Aggregation of Distributions for Diverse Task (2312.02132v3)

Abstract: The Private Aggregation of Teacher Ensembles (PATE) framework enables privacy-preserving machine learning by aggregating responses from disjoint subsets of sensitive data. Adaptations of PATE to tasks with inherent output diversity such as text generation face a core tension: preserving output diversity reduces teacher agreement, which in turn increases the noise required for differential privacy, degrading utility. Yet suppressing diversity is counterproductive, as modern LLMs encapsulate knowledge in their output distributions. We propose Hot PATE, a variant tailored to settings where outputs are distributions. We formally define what it means to preserve diversity and introduce an efficient aggregation mechanism that transfers diversity to the randomized output without incurring additional privacy cost. Our method can be implemented with only API access to proprietary models and serves as a drop-in replacement for existing "cold" PATE aggregators. Empirically, Hot PATE achieves orders-of-magnitude improvement on in-context learning tasks.