Pith. sign in

REVIEW 12 references

On Equivariant Model Selection through the Lens of Uncertainty

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.18629 v2 pith:ZJZOZKNL submitted 2025-06-23 cs.LG stat.ML

Putri A. van der Linden , Alexander Timans , Dharmesh Tailor , Erik J. Bekkers This is my paper
classification cs.LGstat.ML
keywords modelbayesianselectionuncertaintyconstraintsequivariantmodelsperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Equivariant models leverage prior knowledge on symmetries to improve predictive performance, but misspecified architectural constraints can harm it instead. While work has explored learning or relaxing constraints, selecting among pretrained models with varying symmetry biases remains challenging. We examine this model selection task from an uncertainty-aware perspective, comparing frequentist (via Conformal Prediction), Bayesian (via the marginal likelihood), and calibration-based measures to naive error-based evaluation. We find that uncertainty metrics generally align with predictive performance, but Bayesian model evidence does so inconsistently. We attribute this to a mismatch in Bayesian and geometric notions of model complexity for the employed last-layer Laplace approximation, and discuss possible remedies. Our findings point towards the potential of uncertainty in guiding symmetry-aware model selection.

Discussion (0). Sign in to comment.

Reference graph

Works this paper leans on

12 extracted references · 1 linked inside Pith

  1. [1]

    Conformal prediction: A gentle introduction

    Anastasios N Angelopoulos, Stephen Bates, et al. Conformal prediction: A gentle introduction. Foundations and Trends in Machine Learning, 2023

    2023

  2. [2]

    Geometric deep learning on molecular representations

    Kenneth Atz, Francesca Grisoni, and Gisbert Schneider. Geometric deep learning on molecular representations. Nature Machine Intelligence, 2021

    2021

  3. [3]

    E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials

    Simon Batzner, Albert Musaelian, Lixin Sun, Mario Geiger, Jonathan P Mailoa, Mordechai Kornbluth, Nicola Molinari, Tess E Smidt, and Boris Kozinsky. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nature Communications, 2022

    2022

  4. [4]

    The need for uncertainty quantification in machine-assisted medical decision making

    Edmon Begoli, Tanmoy Bhattacharya, and Dimitri Kusnezov. The need for uncertainty quantification in machine-assisted medical decision making. Nature Machine Intelligence, 2019

    2019

  5. [5]

    Fast, expressive se(n)-equivariant networks through weight-sharing in position-orientation space

    Erik J Bekkers, Sharvaree Vadgama, Rob Hesselink, Putri A Van der Linden, and David W Romero. Fast, expressive se(n)-equivariant networks through weight-sharing in position-orientation space. International Conference on Learning Representations, 2024

    2024

  6. [6]

    Pattern recognition and machine learning

    Christopher M Bishop. Pattern recognition and machine learning. Springer, 2006

    2006

  7. [7]

    Probabilistic symmetries and invariant neural networks

    Benjamin Bloem-Reddy, Yee Whye, et al. Probabilistic symmetries and invariant neural networks. Journal of Machine Learning Research, 2020

    2020

  8. [8]

    Geometric and physical quantities improve e (3) equivariant message passing

    Johannes Brandstetter, Rob Hesselink, Elise van der Pol, Erik J Bekkers, and Max Welling. Geometric and physical quantities improve e (3) equivariant message passing. International Conference on Learning Representations, 2021

    2021

Show all 12 references
  1. [9]

    Verification of forecasts expressed in terms of probability

    Glenn W Brier. Verification of forecasts expressed in terms of probability. Monthly Weather Review, 1950

    1950

  2. [10]

    Geometric deep learning: Grids, groups, graphs, geodesics, and gauges

    Michael M Bronstein, Joan Bruna, Taco Cohen, and Petar Veli c kovi \'c . Geometric deep learning: Grids, groups, graphs, geodesics, and gauges. arXiv Preprint (arXiv:2104.13478), 2021

    2021 arXiv

  3. [11]

    Uncertainty quantification with graph neural networks for efficient molecular design

    Lung-Yi Chen and Yi-Pei Li. Uncertainty quantification with graph neural networks for efficient molecular design. Nature Communications, 2025

    2025

  4. [12]

    Group equivariant convolutional networks

    Taco Cohen and Max Welling. Group equivariant convolutional networks. International Conference on Machine Learning, 2016

    2016

Pith tools