AiGAS-dEVL-RC

AiGAS-dEVL-RC: An Adaptive Growing Neural Gas Model for Recurrently Drifting Unsupervised Data Streams

Python implementation and results corresponding to the work:

M. Arostegi, M. N. Bilbao, J. L. Lobo, J. Del Ser, "AiGAS-dEVL-RC: An Adaptive Growing Neural Gas Model for Recurrently Drifting Unsupervised Data Streams". 30 June - 5 July 2025. Rome, Italy. IEEE proceedings of IJCNN 2025.

Concept drift and extreme verification latency pose significant challenges in data stream learning, particularly when dealing with recurring concept changes in dynamic environments. This work introduces a novel method based on the Growing Neural Gas (GNG) algorithm, designed to effectively handle abrupt recurrent drifts while adapting to incrementally evolving data distributions (incremental drifts). Leveraging the self-organizing and topological adaptability of GNG, the proposed approach maintains a compact yet informative memory structure, allowing it to efficiently store and retrieve knowledge of past or recurring concepts, even under conditions of delayed or sparse stream supervision. Our experiments highlight the superiority of our approach over existing data stream learning methods designed to cope with incremental non-stationarities and verification latency, demonstrating its ability to quickly adapt to new drifts, robustly manage recurring patterns, and maintain high predictive accuracy with a minimal memory footprint. Unlike other techniques that fail to leverage recurring knowledge, our proposed approach is proven to be a robust and efficient online learning solution for unsupervised drifting data flows.

The code implementing the AiGAS-dEVL approach described above is currently being polished intensively. We expect to upload it soon, together with instructions to run it in a local Python repository. It will be provided under request. Results files have been uploaded: a file for each dataset, following the format:

Sample at time 1: Feature1, Feature2, ... FeatureN, TrueLabel

Sample at time 2: Feature1, Feature2, ... FeatureN, TrueLabel

...

Sample at time Ts: Feature1, Feature2, ... FeatureN, TrueLabel, PredictedLabel

Sample at time Ts+1: Feature1, Feature2, ... FeatureN, TrueLabel, PredictedLabel

Sample at time Ts+2: Feature1, Feature2, ... FeatureN, TrueLabel, PredictedLabel

...

For more information, please contact the corresponding author (Maria Arostegi, maria.arostegi@tecnalia.com).

Please cite this work as:

@article{arostegi2025aigas-devl-rc,

title={AiGAS-dEVL-RC: An Adaptive Growing Neural Gas Model for Recurrently Drifting Unsupervised Data Streams},

author={Arostegi, Maria and Bilbao, Miren Nekane and Lobo, Jesus L and Del Ser, Javier},

journal={arXiv preprint arXiv: },

year={2025}

}