Operationalize Self-Managing Machine Learning Systems with a Generalizable Knowledge-Driven Architecture

A generalisable Knowledge-Driven Architecture (KDA) that operationalises self-managing ML systems by embedding semantic models in a Knowledge Graph. Declarative probes drive automated integrity monitoring and MAPE-K reconfiguration, achieving 0.56 s adaptation latency and 97% consumption reliability in a synthetic manufacturing setting – a concrete fit for EU AI Act post-market oversight.

research
knowledge-driven architecture
machine learning
self-adaptive systems
software architecture
Accepted (in press) · 2026 IEEE 23rd International Conference on Software Architecture Companion (ICSA-C). Replication package available via Zenodo.
Authors

Anders Launer Bæk-Petersen

Mahyar T. Moghaddam

Jakob Hviid

Mikkel Baun Kjærgaard

Published

March 14, 2026

Publication (SDU) Replication package

Abstract

Modern Machine Learning Systems (MLSystems) must operate reliably in dynamic environments, yet current approaches offer limited support for system-level integrity analysis, runtime adaptation, and transparent component interactions. This paper introduces a generalizable Knowledge-Driven Architecture (KDA) that operationalises MLSystems by embedding semantic models into a Knowledge Graph (KG), reducing component complexity, formalising relationships, and enabling system-aware behaviour across ML lifecycles.

The KDA incorporates declarative probe definitions for component input and output streams, allowing automated instantiation of integrity-monitoring modules that detect behavioural degradation and trigger adaptive reconfiguration using the MAPE-K methodology. Semantic job descriptions further enable the KDA to optimise data flows and maintain consistent, traceable, and reconfigurable processing pipelines.

We evaluate the approach in a synthetic manufacturing setting through adaptive model switching and dynamic lifecycle management scenarios, achieving 0.56-second adaptation latency and 97% consumption reliability. The results demonstrate that combining semantic abstractions with knowledge-driven operational logic provides an effective foundation for building reliable, transparent, and self-managing MLSystems.

Why this matters

The EU AI Act introduces a risk-based regulatory framework that mandates continuous monitoring, transparency, and post-market oversight for high-risk MLSystems. The KDA shows how an architecture can maintain traceability, enforce semantic constraints, and support ongoing operational governance across ML lifecycles – exactly the kind of property regulators are now asking for.

Citation

Bæk-Petersen, A. L., Moghaddam, M., Hviid, J., & Kjærgaard, M. B. (2026). Operationalize Self-Managing Machine Learning Systems with a Generalizable Knowledge-Driven Architecture. In 2026 IEEE 23rd International Conference on Software Architecture Companion (ICSA-C). IEEE.