Vittoria Vineis

Filippo Betello, Antonio Purificato, Vittoria Vineis et al.

The environmental impact of Artificial Intelligence (AI) is emerging as a significant global concern, particularly regarding model training. In this paper, we introduce GREEN (Guided Recommendations of Energy-Efficient Networks), a novel, inference-time approach for recommending Pareto-optimal AI model configurations that optimize validation performance and energy consumption across diverse AI domains and tasks. Our approach directly addresses the limitations of current eco-efficient neural architecture search methods, which are often restricted to specific architectures or tasks. Central to this work is EcoTaskSet, a dataset comprising training dynamics from over 1767 experiments across computer vision, natural language processing, and recommendation systems using both widely used and cutting-edge architectures. Leveraging this dataset and a prediction model, our approach demonstrates effectiveness in selecting the best model configuration based on user preferences. Experimental results show that our method successfully identifies energy-efficient configurations while ensuring competitive performance.

Vittoria Vineis, Giuseppe Perelli, Gabriele Tolomei

Conventional automated decision-support systems, often based on supervised learning, focus on predicting outcomes to recommend actions. However, they typically overlook the complexity of multi-actor environments, where diverse and conflicting stakeholder preferences must be balanced. At the same time, participatory AI approaches remain largely context-specific, limiting their broader applicability. To address these gaps, we propose a participatory framework that reframes decision-making as a multi-stakeholder optimization problem, using context-dependent reward functions to represent each actor's preferences. Our modular, model-agnostic framework employs k-fold cross-validation to fine-tune user-provided prediction models and evaluate decision strategies, including compromise functions that mediate stakeholder trade-offs. A synthetic scoring mechanism aggregates user-defined preferences across multiple metrics to rank strategies and select an optimal decision-maker for generating actionable recommendations on new data. Validated on two high-stake real-world case studies, the framework consistently produces stakeholder-aware decisions that outperform purely predictive baselines across multiple metrics, while enhancing the transparency and accountability of AI-supported decision-making.