Speaker
Description
While many have analyzed the resource efficiency of trained models, an important question remains: How can one be sustainable and resource-aware during AI development, or in other words, when looking for a suitable model to train on a specific learning task? AutoML can help with finding well-performing models on given data, however these frameworks overly focus on predictive quality and neglect performance trade-offs. To answer the calls for sustainable and green AutoML, this poster presents compositional meta-learning (CML). As an explainable approach to model selection, it allows to not only acknowledge multiple performance aspects but also to consider user priorities. With strong generizability and demonstrated effectiveness for time series forecasting and tabular data classification, CML is an important extension to the meta-learning idea and facilitates resource-aware ML.
