• Corpus ID: 235658959

# Hyperbolic Busemann Learning with Ideal Prototypes

@inproceedings{Atigh2021HyperbolicBL,
title={Hyperbolic Busemann Learning with Ideal Prototypes},
author={Mina Ghadimi Atigh and Martin Keller-Ressel and Pascal Mettes},
booktitle={Neural Information Processing Systems},
year={2021}
}
• Published in
Neural Information Processing…
28 June 2021
• Computer Science
Hyperbolic space has become a popular choice of manifold for representation learning of arbitrary data, from tree-like structures and text to graphs. Building on the success of deep learning with prototypes in Euclidean and hyperspherical spaces, a few recent works have proposed hyperbolic prototypes for classification. Such approaches enable effective learning in low-dimensional output spaces and can exploit hierarchical relations amongst classes, but require privileged information about class…

## Figures and Tables from this paper

• Computer Science, Mathematics
ArXiv
• 2022
This work proposes to derive novel hyperbolic sliced-Wasserstein discrepancies based on constructions which use projections on the underlying geodesics either along horospheres or geodesICS, and studies and compares these constructions on different tasks wherehyperbolic representations are relevant.
• Computer Science
ArXiv
• 2022
This work uses tensor ﬁelds (“areas”) to model classes from the geometrical perspective for few-shot learning and presents a simple and effective method, dubbed as hypersphere prototypes ( HyperProto), where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters.
• Computer Science
ArXiv
• 2022
This paper proposes a simple alternative to maximum separation as an inductive bias in the network by adding one matrix multiplication before computing the softmax activations, and illustrates that out-of-distribution and open-set recognition beneﬁt from an embedded maximum separation.
• Computer Science, Mathematics
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 2022
Hyperbolic Image Segmentation opens up new possibilities and practical benefits for segmentation, such as uncertainty estimation and boundary information for free, zero-label generalization, and increased performance in low-dimensional output embeddings.
• Computer Science
ArXiv
• 2023
Hierarchical ProtoPNet is an interpretable network that explains its reasoning process by considering the hierarchical relationship between classes by dissecting the input video frames on multiple levels of the class hierarchy.

## References

SHOWING 1-10 OF 53 REFERENCES

• Computer Science
ICML
• 2019
An approach to learn representations based on the Lorentzian distance in hyperbolic geometry, which makes it appropriate to represent hierarchies where parent nodes minimize the distances to their descendants and have smaller Euclidean norm than their children.
• Computer Science
NeurIPS
• 2018
This work combines the formalism of Mobius gyrovector spaces with the Riemannian geometry of the Poincare model of hyperbolic spaces to derivehyperbolic versions of important deep learning tools: multinomial logistic regression, feed-forward and recurrent neural networks such as gated recurrent units.
• Computer Science
NIPS
• 2017
This work introduces a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an n-dimensional Poincare ball -- and introduces an efficient algorithm to learn the embeddings based on Riemannian optimization.
• Computer Science, Mathematics
AISTATS
• 2019
Hyperbolic SVM, a hyperbolic formulation of support vector machine classifiers, is introduced and its theoretical connection to the Euclidean counterpart is described, allowing end-to-end analyses based on the inherenthyperbolic geometry of the data without resorting to ill-fitting tools developed for Euclidan space.
• Computer Science
ICML
• 2018
A hyperbolic generalization of multidimensional scaling (h-MDS), which offers consistently low distortion even with few dimensions across several datasets, is proposed and a PyTorch-based implementation is designed that can handle incomplete information and is scalable.
• Computer Science
ICLR
• 2019
Empirically, based on extensive experiments, it is proved that the embeddings, trained unsupervised, are the first to simultaneously outperform strong and popular baselines on the tasks of similarity, analogy and hypernymy detection.
• Computer Science, Mathematics
ICML
• 2020
The Fréchet mean is applied to the existing Hyperbolic Graph Convolutional Network, replacing its projected aggregation to obtain state-of-the-art results on datasets with high hyperbolicity and ahyperbolic batch normalization method is developed that gives an improvement parallel to the one observed in the Euclidean setting.
• Computer Science
ICML
• 2018
This work presents a novel method to embed directed acyclic graphs through hierarchical relations as partial orders defined using a family of nested geodesically convex cones and proves that these entailment cones admit an optimal shape with a closed form expression both in the Euclidean and hyperbolic spaces.
• Computer Science
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 2020
A Hyperbolic Visual Embedding Learning Network for zero-shot recognition that is more robust because the embedding feature in hyperbolic space better represents class hierarchy and thereby avoid misleading resulted from unrelated siblings.
• Computer Science
NeurIPS
• 2019
This work proposes a new model which uses an integer-based tiling to represent \emph{any} point in hyperbolic space with provably bounded numerical error, and enables us to store the resulting embeddings with fewer bits.