14 April 2025, publication

Uncertainty-aware recommendation with Bayesian deep ensembles

BDECF combines Bayesian neural networks with deep ensembles so a recommender can report how certain it is, not only what it predicts.

Recommenders trained on sparse explicit feedback are most confident exactly where they have the least evidence. BDECF carries epistemic uncertainty in its weights and aggregates an ensemble, so disagreement between members becomes a usable signal.

Related publication

Epistemic Uncertainty-aware Recommendation Systems via Bayesian Deep Ensemble Learning

Radin Cheraghi, Amir Mohammad Mahfoozi, Sepehr Zolfaghari, Mohammadshayan Shabani, Maryam Ramezani, Hamid R. Rabiee

arXiv preprint, 2025Preprint

arXiv

BibTeX

@misc{cheraghi2025epistemic,
  title = {{Epistemic Uncertainty-aware Recommendation Systems via Bayesian Deep Ensemble Learning}},
  author = {Radin Cheraghi and Amir Mohammad Mahfoozi and Sepehr Zolfaghari and Mohammadshayan Shabani and Maryam Ramezani and Hamid R. Rabiee},
  year = {2025},
  eprint = {2504.10753},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.10753}
}