Decentralized Conformal Novelty Detection via Quantized Model Exchange
For multi-agent systems with privacy and bandwidth constraints, this work enables decentralized novelty detection with rigorous FDR control, though it is an incremental extension of conformal inference to a distributed setting.
This work proposes a decentralized framework for novelty detection that controls the global false discovery rate across heterogeneous data sources without sharing raw data, using quantized surrogate models. The method achieves finite-sample FDR guarantees and reduces communication cost while maintaining competitive statistical power.
This work studies decentralized novelty detection with global false discovery rate (FDR) control across heterogeneous composite null distributions, without sharing the raw data due to privacy and bandwidth considerations. We propose a framework based on the exchange of quantized surrogate models, allowing independent agents to share low-precision representations of locally learned non-conformity score functions. We prove that evaluating data against these quantized composite scores preserves conditional exchangeability, providing rigorous finite-sample guarantees for global FDR control. Empirical studies on synthetic datasets confirm our theoretical results, demonstrating that the proposed approach maintains competitive statistical power while drastically reducing the communication cost.