Adaptive Active Inference Agents for Heterogeneous and Lifelong Federated Learning

TL;DR

This paper introduces adaptive active inference agents for heterogeneous federated learning, enabling systems to dynamically balance constraints and adapt to environmental changes with high fulfillment rates.

Contribution

It presents a novel AIF-based framework for high-level system control in heterogeneous pervasive systems, moving beyond low-level SLO optimization.

Findings

Achieved up to 98% fulfillment rate in resource management.

Demonstrated adaptability to environmental changes in a physical testbed.

Validated the approach in a lifelong federated learning scenario.

Abstract

Handling heterogeneity and unpredictability are two core problems in pervasive computing. The challenge is to seamlessly integrate devices with varying computational resources in a dynamic environment to form a cohesive system that can fulfill the needs of all participants. Existing work on adaptive systems typically focuses on optimizing individual variables or low-level Service Level Objectives (SLOs), such as constraining the usage of specific resources. While low-level control mechanisms permit fine-grained control over a system, they introduce considerable complexity, particularly in dynamic environments. To this end, we propose drawing from Active Inference (AIF), a neuroscientific framework for designing adaptive agents. Specifically, we introduce a conceptual agent for heterogeneous pervasive systems that permits setting global systems constraints as high-level SLOs. Instead of manually setting low-level SLOs, the system finds an equilibrium that can adapt to environmental changes. We demonstrate the viability of our AIF agents with an extensive experiment design, using heterogeneous and lifelong federated learning as an application scenario. We conduct our experiments on a physical testbed of devices with different resource types and vendor specifications. The results provide convincing evidence that an AIF agent can adapt a system to environmental changes. In particular, the AIF agent can balance competing SLOs in resource heterogeneous environments to ensure up to 98% fulfillment rate.