Differentiable Model Selection for Ensemble Learning

Abstract

Model selection is a strategy aimed at creating accurate and robust models by identifying the optimal model for classifying any particular input sample. This paper proposes a novel framework for differentiable selection of groups of models by integrating machine learning and combinatorial optimization. The framework is tailored for ensemble learning with a strategy that learns to combine the predictions of appropriately selected pre-trained ensemble models. It does so by modeling the ensemble learning task as a differentiable selection program trained end-to-end over a pretrained ensemble to optimize task performance. The proposed framework demonstrates its versatility and effectiveness, outperforming conventional and advanced consensus rules across a variety of classification tasks.

Cite

Text

Kotary et al. "Differentiable Model Selection for Ensemble Learning." International Joint Conference on Artificial Intelligence, 2023. doi:10.24963/IJCAI.2023/217

Markdown

[Kotary et al. "Differentiable Model Selection for Ensemble Learning." International Joint Conference on Artificial Intelligence, 2023.](https://mlanthology.org/ijcai/2023/kotary2023ijcai-differentiable/) doi:10.24963/IJCAI.2023/217

BibTeX

@inproceedings{kotary2023ijcai-differentiable,
  title     = {{Differentiable Model Selection for Ensemble Learning}},
  author    = {Kotary, James and Di Vito, Vincenzo and Fioretto, Ferdinando},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {1954-1962},
  doi       = {10.24963/IJCAI.2023/217},
  url       = {https://mlanthology.org/ijcai/2023/kotary2023ijcai-differentiable/}
}