English

Differentiating through the Fr\'echet Mean

Machine Learning 2021-07-07 v4 Machine Learning

Abstract

Recent advances in deep representation learning on Riemannian manifolds extend classical deep learning operations to better capture the geometry of the manifold. One possible extension is the Fr\'echet mean, the generalization of the Euclidean mean; however, it has been difficult to apply because it lacks a closed form with an easily computable derivative. In this paper, we show how to differentiate through the Fr\'echet mean for arbitrary Riemannian manifolds. Then, focusing on hyperbolic space, we derive explicit gradient expressions and a fast, accurate, and hyperparameter-free Fr\'echet mean solver. This fully integrates the Fr\'echet mean into the hyperbolic neural network pipeline. To demonstrate this integration, we present two case studies. First, we apply our Fr\'echet mean to the existing Hyperbolic Graph Convolutional Network, replacing its projected aggregation to obtain state-of-the-art results on datasets with high hyperbolicity. Second, to demonstrate the Fr\'echet mean's capacity to generalize Euclidean neural network operations, we develop a hyperbolic batch normalization method that gives an improvement parallel to the one observed in the Euclidean setting.

Keywords

Cite

@article{arxiv.2003.00335,
  title  = {Differentiating through the Fr\'echet Mean},
  author = {Aaron Lou and Isay Katsman and Qingxuan Jiang and Serge Belongie and Ser-Nam Lim and Christopher De Sa},
  journal= {arXiv preprint arXiv:2003.00335},
  year   = {2021}
}

Comments

ICML 2020 camera-ready; updated Algorithm 1 typo

R2 v1 2026-06-23T13:58:56.898Z