Federated Inference with Reliable Uncertainty Quantification over Wireless Channels via Conformal Prediction

TL;DR

This paper introduces a wireless federated conformal prediction protocol that guarantees reliable uncertainty quantification over wireless channels, improving inference accuracy with limited communication resources.

Contribution

It proposes the WFCP protocol combining TBMA and quantile correction, providing formal coverage guarantees in wireless federated inference.

Findings

WFCP outperforms digital federated CP schemes in limited resource regimes.

The protocol guarantees coverage despite wireless channel noise.

Numerical results validate the advantages of WFCP over existing methods.

Abstract

In this paper, we consider a wireless federated inference scenario in which devices and a server share a pre-trained machine learning model. The devices communicate statistical information about their local data to the server over a common wireless channel, aiming to enhance the quality of the inference decision at the server. Recent work has introduced federated conformal prediction (CP), which leverages devices-to-server communication to improve the reliability of the server's decision. With federated CP, devices communicate to the server information about the loss accrued by the shared pre-trained model on the local data, and the server leverages this information to calibrate a decision interval, or set, so that it is guaranteed to contain the correct answer with a pre-defined target reliability level. Previous work assumed noise-free communication, whereby devices can communicate a single real number to the server. In this paper, we study for the first time federated CP in a wireless setting. We introduce a novel protocol, termed wireless federated conformal prediction (WFCP), which builds on type-based multiple access (TBMA) and on a novel quantile correction strategy. WFCP is proved to provide formal reliability guarantees in terms of coverage of the predicted set produced by the server. Using numerical results, we demonstrate the significant advantages of WFCP against digital implementations of existing federated CP schemes, especially in regimes with limited communication resources and/or large number of devices.