Adaptive Active Inference Agents for Heterogeneous and Lifelong Federated Learning

2024-10-09

arXiv.org

AI Summary

This work addresses the resource coordination challenge in ubiquitous computing, arising from device heterogeneity and environmental dynamics. We propose the first Adaptive Agent Framework grounded in Active Inference (AIF), which is driven by high-level service objectives and employs variational Bayesian inference for autonomous decision-making—eliminating reliance on manually specified low-level resource constraints. The framework supports lifelong learning and cross-device collaboration. Its key innovation lies in integrating neuroscience-inspired AIF into federated learning control, enabling a paradigm shift from resource-centric to goal-directed orchestration. Evaluated on a realistic multi-vendor, multi-specification device testbed, our approach achieves a 98% aggregate SLO compliance rate—substantially outperforming conventional methods—while demonstrating robustness to environmental changes and effective multi-objective协同 optimization.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Handling heterogeneity in pervasive computing systems.
• Adapting to unpredictability in dynamic environments.
• Balancing competing Service Level Objectives (SLOs).

Innovation

• Uses Active Inference for adaptive agent design
• Sets global system constraints as high-level SLOs
• Balances competing SLOs in resource heterogeneity