# Adaptive Active Inference Agents for Heterogeneous and Lifelong Federated Learning

arXiv: https://arxiv.org/abs/2410.09099 · HTML: https://mlsanity.com/paper/2410.09099/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 19 of 19)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [River: machine learning for streaming data in Python](https://mlsanity.com/paper/2012.04740/) (2020)
- [A survey of Bayesian Network structure learning](https://mlsanity.com/paper/2109.11415/) (2021)
- [Federated Bayesian Optimization via Thompson Sampling](https://mlsanity.com/paper/2010.10154/) (2020)
- [Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence](https://mlsanity.com/paper/1909.00560/) (2019)
- [FedGTA: Topology-aware Averaging for Federated Graph Learning](https://mlsanity.com/paper/2401.11755/) (2024)
- [Multi-objective Evolutionary Federated Learning](https://mlsanity.com/paper/1812.07478/) (2018)
- [pymdp: A Python library for active inference in discrete state spaces](https://mlsanity.com/paper/2201.03904/) (2022)
- [Federated Learning under Distributed Concept Drift](https://mlsanity.com/paper/2206.00799/) (2022)
- [Designing Ecosystems of Intelligence from First Principles](https://mlsanity.com/paper/2212.01354/) (2022)
- [FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing](https://mlsanity.com/paper/2302.10681/) (2023)
- [Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies](https://mlsanity.com/paper/2109.03999/) (2021)
- [Equilibrium in the Computing Continuum through Active Inference](https://mlsanity.com/paper/2311.16769/) (2023)
- [Adaptive Stream Processing on Edge Devices through Active Inference](https://mlsanity.com/paper/2409.17937/) (2024)
- [Inference Load-Aware Orchestration for Hierarchical Federated Learning](https://mlsanity.com/paper/2407.16836/) (2024)
- [Training Heterogeneous Client Models using Knowledge Distillation in Serverless Federated Learning](https://mlsanity.com/paper/2402.07295/) (2024)

## Built on by (most cited first, 3 of 3)

- [Multi-Dimensional Autoscaling of Stream Processing Services on Edge Devices](https://mlsanity.com/paper/2510.06882/) (2025)
- [Multi-dimensional Autoscaling of Processing Services: A Comparison of Agent-based Methods](https://mlsanity.com/paper/2506.10420/) (2025)
- [Incentives and Evidence in Learned Service Orchestration](https://mlsanity.com/paper/2606.16555/) (2026)

## Abstract (arXiv)

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.