Towards Scalable Hyperbolic Neural Networks using Taylor Series Approximations

• URL: http://arxiv.org/abs/2206.03610v1
• Date: Tue, 7 Jun 2022 22:31:17 GMT
• Title: Towards Scalable Hyperbolic Neural Networks using Taylor Series Approximations
• Authors: Nurendra Choudhary, Chandan K. Reddy
• Abstract summary: Hyperbolic networks have shown prominent improvements over their Euclidean counterparts in several areas involving hierarchical datasets. Their adoption in practice remains restricted due to (i) non-scalability on accelerated deep learning hardware, (ii) vanishing due to the closure of hyperbolic space, and (iii) information loss. We propose the approximation of hyperbolic operators using Taylor series expansions, which allows us to reformulate the tangent gradients of hyperbolic functions into their equivariants.
• Score: 10.056167107654089
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hyperbolic networks have shown prominent improvements over their Euclidean counterparts in several areas involving hierarchical datasets in various domains such as computer vision, graph analysis, and natural language processing. However, their adoption in practice remains restricted due to (i) non-scalability on accelerated deep learning hardware, (ii) vanishing gradients due to the closure of hyperbolic space, and (iii) information loss due to frequent mapping between local tangent space and fully hyperbolic space. To tackle these issues, we propose the approximation of hyperbolic operators using Taylor series expansions, which allows us to reformulate the computationally expensive tangent and cosine hyperbolic functions into their polynomial equivariants which are more efficient. This allows us to retain the benefits of preserving the hierarchical anatomy of the hyperbolic space, while maintaining the scalability over current accelerated deep learning infrastructure. The polynomial formulation also enables us to utilize the advancements in Euclidean networks such as gradient clipping and ReLU activation to avoid vanishing gradients and remove errors due to frequent switching between tangent space and hyperbolic space. Our empirical evaluation on standard benchmarks in the domain of graph analysis and computer vision shows that our polynomial formulation is as scalable as Euclidean architectures, both in terms of memory and time complexity, while providing results as effective as hyperbolic models. Moreover, our formulation also shows a considerable improvement over its baselines due to our solution to vanishing gradients and information loss.

Related papers

• Optimizing Curvature Learning for Robust Hyperbolic Deep Learning in Computer Vision [3.3964154468907486]
  We introduce an improved schema for popular learning algorithms and a novel normalization approach to constrain embeddings within the variable representative radius of the manifold. Our approach demonstrates consistent performance improvements across both direct classification and hierarchical metric learning tasks while allowing for larger hyperbolic models.
  arXiv  Detail & Related papers  (2024-05-22T20:30:14Z)
• DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling [0.20287200280084108]
  We learn a hyperbolic scaling of the unsigned distance field, which defines a new Eikonal problem with distinct boundary conditions. Our approach not only addresses the challenge of open surface representation but also demonstrates significant improvement in reconstruction quality and training performance.
  arXiv  Detail & Related papers  (2024-02-14T00:42:19Z)
• Improving embedding of graphs with missing data by soft manifolds [51.425411400683565]
  The reliability of graph embeddings depends on how much the geometry of the continuous space matches the graph structure. We introduce a new class of manifold, named soft manifold, that can solve this situation. Using soft manifold for graph embedding, we can provide continuous spaces to pursue any task in data analysis over complex datasets.
  arXiv  Detail & Related papers  (2023-11-29T12:48:33Z)
• Fast hyperboloid decision tree algorithms [0.6656737591902598]
  We present hyperDT, a novel extension of decision tree algorithms into hyperbolic space. Our approach is conceptually straightforward and maintains constant-time decision complexity. Building upon hyperDT we introduce hyperRF, a hyperbolic random forest model.
  arXiv  Detail & Related papers  (2023-10-20T22:31:10Z)
• Hyperbolic Graph Neural Networks: A Review of Methods and Applications [55.5502008501764]
  Graph neural networks generalize conventional neural networks to graph-structured data. The performance of Euclidean models in graph-related learning is still bounded and limited by the representation ability of Euclidean geometry. Recently, hyperbolic space has gained increasing popularity in processing graph data with tree-like structure and power-law distribution.
  arXiv  Detail & Related papers  (2022-02-28T15:08:48Z)
• HyLa: Hyperbolic Laplacian Features For Graph Learning [44.33054069927441]
  hyperbolic space can support embeddings of tree- and graph-structured data. For graph learning, points in hyperbolic space have been used successfully as signals in deep neural networks. Existing hyperbolic networks are computationally expensive and can be numerically unstable. We propose HyLa, a completely different approach to using hyperbolic space in graph learning.
  arXiv  Detail & Related papers  (2022-02-14T16:40:24Z)
• Enhancing Hyperbolic Graph Embeddings via Contrastive Learning [7.901082408569372]
  We propose a novel Hyperbolic Graph Contrastive Learning (HGCL) framework which learns node representations through multiple hyperbolic spaces. Experimental results on multiple real-world datasets demonstrate the superiority of the proposed HGCL.
  arXiv  Detail & Related papers  (2022-01-21T06:10:05Z)
• Cogradient Descent for Dependable Learning [64.02052988844301]
  We propose a dependable learning based on Cogradient Descent (CoGD) algorithm to address the bilinear optimization problem. CoGD is introduced to solve bilinear problems when one variable is with sparsity constraint. It can also be used to decompose the association of features and weights, which further generalizes our method to better train convolutional neural networks (CNNs)
  arXiv  Detail & Related papers  (2021-06-20T04:28:20Z)
• Fully Hyperbolic Neural Networks [63.22521652077353]
  We propose a fully hyperbolic framework to build hyperbolic networks based on the Lorentz model. We show that our method has better performance for building both shallow and deep networks.
  arXiv  Detail & Related papers  (2021-05-31T03:36:49Z)
• InverseForm: A Loss Function for Structured Boundary-Aware Segmentation [80.39674800972182]
  We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network. This plug-in loss term complements the cross-entropy loss in capturing boundary transformations. We analyze the quantitative and qualitative effects of our loss function on three indoor and outdoor segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-04-06T18:52:45Z)
• Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference [48.63194907060615]
  We build off of semi-implicit graph variational auto-encoders to capture higher-order statistics in a low-dimensional graph latent representation. We incorporate hyperbolic geometry in the latent space through a Poincare embedding to efficiently represent graphs exhibiting hierarchical structure.
  arXiv  Detail & Related papers  (2020-10-31T05:48:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.