Causal Influence in Federated Edge Inference

TL;DR

This paper introduces a causal framework to quantify the influence of heterogeneous agents in federated edge inference, enhancing understanding of decision-making and robustness in multi-agent systems.

Contribution

It develops a causal approach to measure agent influence in federated inference, addressing scenarios with partial data and diverse participation patterns.

Findings

Derived expressions for causal impact of agents on decisions

Validated theoretical results with simulations and real-world crowd counting

Identified potential for detecting adversarial attacks or malfunctions

Abstract

In this paper, we consider a setting where heterogeneous agents with connectivity are performing inference using unlabeled streaming data. Observed data are only partially informative about the target variable of interest. In order to overcome the uncertainty, agents cooperate with each other by exchanging their local inferences with and through a fusion center. To evaluate how each agent influences the overall decision, we adopt a causal framework in order to distinguish the actual influence of agents from mere correlations within the decision-making process. Various scenarios reflecting different agent participation patterns and fusion center policies are investigated. We derive expressions to quantify the causal impact of each agent on the joint decision, which could be beneficial for anticipating and addressing atypical scenarios, such as adversarial attacks or system malfunctions. We validate our theoretical results with numerical simulations and a real-world application of multi-camera crowd counting.