Our partner CeADAR actively contributed to the ECML-PKDD 2025 SynDaiTE workshop, presenting both a poster and a talk on their paper DriftMoE: A Mixture of Experts Approach to Handle Concept Drifts.
The paper introduces a state-of-the-art architecture for real-time data streams affected by concept drift, leveraging a Mixture of Experts (MoE) approach that significantly reduces resource requirements and is well-suited for deployment across the cloud-edge continuum.
The methodology outlined in DriftMoE holds strong potential for adaptation within O-CEI Task 3.5 (Implementation of intra- and cross-domain data management, observability, and AI orchestration mechanisms), where CeADAR plays a leading role. The intent is to use router networks to recommend relevant models from O-CEI’s marketplace. Furthermore, CeADAR is investigating ways to compress a MoE, which would make it even more efficient for recommending resource-intensive models like LLMs, a key part of our future research efforts. The paper acknowledges O-CEI.
Event website: