Towards Node Liability in Federated Learning: Computational Cost and Network Overhead

TL;DR

This paper introduces NL-FL, a methodology for identifying the data source nodes responsible for specific decisions in federated learning, addressing accountability and improving model accuracy by excluding misbehaving nodes.

Contribution

The paper proposes NL-FL, a novel approach to trace decision sources in federated learning, and evaluates its computational and network costs in practical scenarios.

Findings

NL-FL can quickly identify misbehaving nodes.

NL-FL improves learning accuracy by excluding untrustworthy nodes.

NL-FL's overhead is manageable in edge-based environments.

Abstract

Many machine learning (ML) techniques suffer from the drawback that their output (e.g., a classification decision) is not clearly and intuitively connected to their input (e.g., an image). To cope with this issue, several explainable ML techniques have been proposed to, e.g., identify which pixels of an input image had the strongest influence on its classification. However, in distributed scenarios, it is often more important to connect decisions with the information used for the model training and the nodes supplying such information. To this end, in this paper we focus on federated learning and present a new methodology, named node liability in federated learning (NL-FL), which permits to identify the source of the training information that most contributed to a given decision. After discussing NL-FL's cost in terms of extra computation, storage, and network latency, we demonstrate its usefulness in an edge-based scenario. We find that NL-FL is able to swiftly identify misbehaving nodes and to exclude them from the training process, thereby improving learning accuracy.