Provably Accurate and Scalable Linear Classifiers in Hyperbolic Spaces

by   Chao Pan, et al.
University of Illinois at Urbana-Champaign

Many high-dimensional practical data sets have hierarchical structures induced by graphs or time series. Such data sets are hard to process in Euclidean spaces and one often seeks low-dimensional embeddings in other space forms to perform the required learning tasks. For hierarchical data, the space of choice is a hyperbolic space because it guarantees low-distortion embeddings for tree-like structures. The geometry of hyperbolic spaces has properties not encountered in Euclidean spaces that pose challenges when trying to rigorously analyze algorithmic solutions. We propose a unified framework for learning scalable and simple hyperbolic linear classifiers with provable performance guarantees. The gist of our approach is to focus on Poincaré ball models and formulate the classification problems using tangent space formalisms. Our results include a new hyperbolic perceptron algorithm as well as an efficient and highly accurate convex optimization setup for hyperbolic support vector machine classifiers. Furthermore, we adapt our approach to accommodate second-order perceptrons, where data is preprocessed based on second-order information (correlation) to accelerate convergence, and strategic perceptrons, where potentially manipulated data arrives in an online manner and decisions are made sequentially. The excellent performance of the Poincaré second-order and strategic perceptrons shows that the proposed framework can be extended to general machine learning problems in hyperbolic spaces. Our experimental results, pertaining to synthetic, single-cell RNA-seq expression measurements, CIFAR10, Fashion-MNIST and mini-ImageNet, establish that all algorithms provably converge and have complexity comparable to those of their Euclidean counterparts. Accompanying codes can be found at:


page 3

page 4

page 5

page 6

page 8

page 9

page 12

page 16


Highly Scalable and Provably Accurate Classification in Poincare Balls

Many high-dimensional and large-volume data sets of practical relevance ...

Linear Classifiers in Mixed Constant Curvature Spaces

Embedding methods for mixed-curvature spaces are powerful techniques for...

Hyperbolic Entailment Cones for Learning Hierarchical Embeddings

Learning graph representations via low-dimensional embeddings that prese...

Robust Large-Margin Learning in Hyperbolic Space

Recently, there has been a surge of interest in representation learning ...

Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex Hulls

Hierarchical and tree-like data sets arise in many applications, includi...

Aligning Hyperbolic Representations: an Optimal Transport-based approach

Hyperbolic-spaces are better suited to represent data with underlying hi...

Probing BERT in Hyperbolic Spaces

Recently, a variety of probing tasks are proposed to discover linguistic...

Please sign up or login with your details

Forgot password? Click here to reset