# Equilibrium in the Computing Continuum through Active Inference

arXiv: https://arxiv.org/abs/2311.16769 · HTML: https://mlsanity.com/paper/2311.16769/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 67 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Builds on (most cited first, 13 of 13)

- [D'ya like DAGs? A Survey on Structure Learning and Causal Discovery](https://mlsanity.com/paper/2103.02582/) (2021)
- [Learning to cluster in order to transfer across domains and tasks](https://mlsanity.com/paper/1711.10125/) (2017)
- [pymdp: A Python library for active inference in discrete state spaces](https://mlsanity.com/paper/2201.03904/) (2022)
- [Discovering Causal Relations and Equations from Data](https://mlsanity.com/paper/2305.13341/) (2023)
- [The free energy principle made simpler but not too simple](https://mlsanity.com/paper/2201.06387/) (2022)
- [pgmpy: A Python Toolkit for Bayesian Networks](https://mlsanity.com/paper/2304.08639/) (2023)
- [A Review of the Role of Causality in Developing Trustworthy AI Systems](https://mlsanity.com/paper/2302.06975/) (2023)
- [Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration](https://mlsanity.com/paper/2205.01423/) (2022)
- [The Case for Retraining of ML Models for IoT Device Identification at the Edge](https://mlsanity.com/paper/2011.08605/) (2020)
- [Monitoring and Adapting ML Models on Mobile Devices](https://mlsanity.com/paper/2305.07772/) (2023)
- [Designing Reconfigurable Intelligent Systems with Markov Blankets](https://mlsanity.com/paper/2311.10597/) (2023)
- [Active Inference on the Edge: A Design Study](https://mlsanity.com/paper/2311.10607/) (2023)
- [A Novel Load Balancing Scheme for Mobile Edge Computing](https://mlsanity.com/paper/2112.10091/) (2021)

## Built on by (most cited first, 9 of 9)

- [Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey](https://mlsanity.com/paper/2505.01821/) (2025)
- [Adaptive Stream Processing on Edge Devices through Active Inference](https://mlsanity.com/paper/2409.17937/) (2024)
- [Benchmarking Dynamic SLO Compliance in Distributed Computing Continuum Systems](https://mlsanity.com/paper/2503.03274/) (2025)
- [Adaptive Active Inference Agents for Heterogeneous and Lifelong Federated Learning](https://mlsanity.com/paper/2410.09099/) (2024)
- [A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks](https://mlsanity.com/paper/2508.18803/) (2025)
- [A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems](https://mlsanity.com/paper/2502.06581/) (2025)
- [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)
- [An Uncertainty-Aware Resilience Micro-Agent for Causal Observability in the Computing Continuum](https://mlsanity.com/paper/2605.10718/) (2026)

## Abstract (arXiv)

Computing Continuum (CC) systems are challenged to ensure the intricate requirements of each computational tier. Given the system's scale, the Service Level Objectives (SLOs) which are expressed as these requirements, must be broken down into smaller parts that can be decentralized. We present our framework for collaborative edge intelligence enabling individual edge devices to (1) develop a causal understanding of how to enforce their SLOs, and (2) transfer knowledge to speed up the onboarding of heterogeneous devices. Through collaboration, they (3) increase the scope of SLO fulfillment. We implemented the framework and evaluated a use case in which a CC system is responsible for ensuring Quality of Service (QoS) and Quality of Experience (QoE) during video streaming. Our results showed that edge devices required only ten training rounds to ensure four SLOs; furthermore, the underlying causal structures were also rationally explainable. The addition of new types of devices can be done a posteriori, the framework allowed them to reuse existing models, even though the device type had been unknown. Finally, rebalancing the load within a device cluster allowed individual edge devices to recover their SLO compliance after a network failure from 22% to 89%.