Towards Uncertainty-Aware Federated Granger Causal Learning

TL;DR

This paper develops an uncertainty-aware federated Granger causality framework that quantifies and tests the reliability of inferred cross-client interactions in distributed time-series data.

Contribution

It introduces a theoretical analysis of uncertainty propagation in federated Granger causality and proposes a hypothesis testing method to identify genuine causal links.

Findings

Uncertainty propagation matches theoretical predictions across regimes.

The method outperforms existing federated causal structure learning baselines.

Steady-state uncertainty depends only on client data statistics, not priors.

Abstract

Granger causality recovers directed interactions from time-series data, but in many distributed systems, the data are vertically partitioned across clients, with each client observing only the variables of its own subsystem. Federated Granger causality (FedGC) recovers cross-client interactions without sharing raw data. Existing FedGC methods, however, return deterministic point estimates with no calibrated measure of uncertainty, leaving operators without a principled basis for identifying reliable cross-client interactions. We address this limitation by characterizing how uncertainty propagates through the FedGC framework. We derive closed-form covariance recursions for the cross-covariances induced by the coupled client-server feedback loop, and establish spectral-radius-based convergence conditions yielding closed-form expressions for the steady-state variances at both the client and server. Under mild stability conditions, we prove that the steady-state uncertainty depends only on client data statistics (aleatoric) and is independent of the priors placed on the model parameters (epistemic). Building on this asymptotic characterization, we construct a post-training hypothesis testing procedure that separates genuine cross-client interactions from spurious edges. Experiments on synthetic and real-world datasets show that the predicted uncertainty propagation matches the theory across multiple operating regimes, while consistently outperforming the state-of-the-art federated causal structure learning baselines.