# Decentralized Conformal Novelty Detection via Quantized Model Exchange

arXiv: https://arxiv.org/abs/2605.08263 · HTML: https://mlsanity.com/paper/2605.08263/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 8 of 8)

- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)
- [Testing for Outliers with Conformal p-values](https://mlsanity.com/paper/2104.08279/) (2021)
- [Theoretical Foundations of Conformal Prediction](https://mlsanity.com/paper/2411.11824/) (2024)
- [Adaptive novelty detection with false discovery rate guarantee](https://mlsanity.com/paper/2208.06685/) (2022)
- [QuTE: decentralized multiple testing on sensor networks with false discovery rate control](https://mlsanity.com/paper/2210.04334/) (2022)
- [Distributed Multiple Testing with False Discovery Rate Control in the Presence of Byzantines](https://mlsanity.com/paper/2501.13242/) (2025)
- [A more practical approach for the Benjamini-Hochberg FDR controlling procedure for huge-scale testing problems](https://mlsanity.com/paper/1501.05225/) (2015)
- [On Large-Scale Multiple Testing Over Networks: An Asymptotic Approach](https://mlsanity.com/paper/2211.16059/) (2022)

## Abstract (arXiv)

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.