# Adaptive Stream Processing on Edge Devices through Active Inference

arXiv: https://arxiv.org/abs/2409.17937 · HTML: https://mlsanity.com/paper/2409.17937/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 69 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Builds on (most cited first, 15 of 15)

- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [A survey of Bayesian Network structure learning](https://mlsanity.com/paper/2109.11415/) (2021)
- [Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence](https://mlsanity.com/paper/1909.00560/) (2019)
- [Reinforcement Learning through Active Inference](https://mlsanity.com/paper/2002.12636/) (2020)
- [pymdp: A Python library for active inference in discrete state spaces](https://mlsanity.com/paper/2201.03904/) (2022)
- [Real-Time Video Inference on Edge Devices via Adaptive Model Streaming](https://mlsanity.com/paper/2006.06628/) (2020)
- [Designing Ecosystems of Intelligence from First Principles](https://mlsanity.com/paper/2212.01354/) (2022)
- [pgmpy: A Python Toolkit for Bayesian Networks](https://mlsanity.com/paper/2304.08639/) (2023)
- [Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing Systems](https://mlsanity.com/paper/2005.02459/) (2020)
- [A Review of the Role of Causality in Developing Trustworthy AI Systems](https://mlsanity.com/paper/2302.06975/) (2023)
- [Equilibrium in the Computing Continuum through Active Inference](https://mlsanity.com/paper/2311.16769/) (2023)
- [Designing Reconfigurable Intelligent Systems with Markov Blankets](https://mlsanity.com/paper/2311.10597/) (2023)
- [Artificial Intelligence (AI)-Centric Management of Resources in Modern Distributed Computing Systems](https://mlsanity.com/paper/2006.05075/) (2020)
- [Vehicle Speed Aware Computing Task Offloading and Resource Allocation Based on Multi-Agent Reinforcement Learning in a Vehicular Edge Computing Network](https://mlsanity.com/paper/2008.06641/) (2020)
- [Active Inference on the Edge: A Design Study](https://mlsanity.com/paper/2311.10607/) (2023)

## Built on by (most cited first, 6 of 6)

- [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)
- [NeSy-Edge: Neuro-Symbolic Trustworthy Self-Healing in the Computing Continuum](https://mlsanity.com/paper/2603.21145/) (2026)
- [Active Multimodal Distillation for Few-shot Action Recognition](https://mlsanity.com/paper/2506.13322/) (2025)
- [A Microservice-Based Platform for Sustainable and Intelligent SLO Fulfilment and Service Management](https://mlsanity.com/paper/2602.12875/) (2026)
- [An Uncertainty-Aware Resilience Micro-Agent for Causal Observability in the Computing Continuum](https://mlsanity.com/paper/2605.10718/) (2026)

## Abstract (arXiv)

The current scenario of IoT is witnessing a constant increase on the volume of data, which is generated in constant stream, calling for novel architectural and logical solutions for processing it. Moving the data handling towards the edge of the computing spectrum guarantees better distribution of load and, in principle, lower latency and better privacy. However, managing such a structure is complex, especially when requirements, also referred to Service Level Objectives (SLOs), specified by applications' owners and infrastructure managers need to be ensured. Despite the rich number of proposals of Machine Learning (ML) based management solutions, researchers and practitioners yet struggle to guarantee long-term prediction and control, and accurate troubleshooting. Therefore, we present a novel ML paradigm based on Active Inference (AIF) -- a concept from neuroscience that describes how the brain constantly predicts and evaluates sensory information to decrease long-term surprise. We implement it and evaluate it in a heterogeneous real stream processing use case, where an AIF-based agent continuously optimizes the fulfillment of three SLOs for three autonomous driving services running on multiple devices. The agent used causal knowledge to gradually develop an understanding of how its actions are related to requirements fulfillment, and which configurations to favor. Through this approach, our agent requires up to thirty iterations to converge to the optimal solution, showing the capability of offering accurate results in a short amount of time. Furthermore, thanks to AIF and its causal structures, our method guarantees full transparency on the decision making, making the interpretation of the results and the troubleshooting effortless.