Hyperbolic Manifold Regression

Geometric representation learning has recently shown great promise in several machine learning settings, ranging from relational learning to language processing and generative models. In this work, we consider the problem of performing manifold-valued regression onto an hyperbolic space as an intermediate component for a number of relevant machine learning applications. In particular, by formulating the problem of predicting nodes of a tree as a manifold regression task in the hyperbolic space, we propose a novel perspective on two challenging tasks: 1) hierarchical classification via label embeddings and 2) taxonomy extension of hyperbolic representations. To address the regression problem we consider previous methods as well as proposing two novel approaches that are computationally more advantageous: a parametric deep learning model that is informed by the geodesics of the target space and a non-parametric kernel-method for which we also prove excess risk bounds. Our experiments show that the strategy of leveraging the hyperbolic geometry is promising. In particular, in the taxonomy expansion setting, we find that the hyperbolic-based estimators significantly outperform methods performing regression in the ambient Euclidean space.

[1]  Christopher De Sa,et al.  Representation Tradeoffs for Hyperbolic Embeddings , 2018, ICML.

[2]  Bernhard Schölkopf,et al.  Nonparametric Regression between General Riemannian Manifolds , 2010, SIAM J. Imaging Sci..

[3]  Nicola De Cao,et al.  Hyperspherical Variational Auto-Encoders , 2018, UAI 2018.

[4]  Azad Naik,et al.  Large Scale Hierarchical Classification: State of the Art , 2018, SpringerBriefs in Computer Science.

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Xiaogang Wang,et al.  Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Emmanuel Hebey Nonlinear analysis on manifolds: Sobolev spaces and inequalities , 1999 .

[8]  King-Sun Fu,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Gökhan BakIr,et al.  Predicting Structured Data , 2008 .

[10]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[11]  Peerapon Vateekul,et al.  Hierarchical multi-label classification with SVMs: A case study in gene function prediction , 2014, Intell. Data Anal..

[12]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[13]  Fabio Daolio,et al.  Scalable Hyperbolic Recommender Systems , 2019, ArXiv.

[14]  Le Song,et al.  A unified kernel framework for nonparametric inference in graphical models ] Kernel Embeddings of Conditional Distributions , 2013 .

[15]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[16]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Juhan Nam,et al.  Multimodal Deep Learning , 2011, ICML.

[18]  Hans-Peter Kriegel,et al.  A Three-Way Model for Collective Learning on Multi-Relational Data , 2011, ICML.

[19]  Yoshua Bengio,et al.  On Using Very Large Target Vocabulary for Neural Machine Translation , 2014, ACL.

[20]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[21]  Gary Bécigneul,et al.  Poincaré GloVe: Hyperbolic Word Embeddings , 2018, ICLR.

[22]  Douwe Kiela,et al.  Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry , 2018, ICML.

[23]  Serge J. Belongie,et al.  Separating Self-Expression and Visual Content in Hashtag Supervision , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Bhargav Srinivasa Desikan,et al.  Natural Language Processing and Computational Linguistics , 2018 .

[25]  Nicola De Cao,et al.  Explorations in Homeomorphic Variational Auto-Encoding , 2018, ArXiv.

[26]  Thomas Hofmann,et al.  Hyperbolic Neural Networks , 2018, NeurIPS.

[27]  Florian Steinke,et al.  Non-parametric Regression Between Manifolds , 2008, NIPS.

[28]  Matt Le,et al.  Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings , 2019, ACL.

[29]  Gaven Martin Balls in Hyperbolic Manifolds , 1989 .

[30]  Jiacheng Xu,et al.  Spherical Latent Spaces for Stable Variational Autoencoders , 2018, EMNLP.

[31]  François Chollet Information-theoretical label embeddings for large-scale image classification , 2016, ArXiv.

[32]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[33]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[34]  Lorenzo Rosasco,et al.  Manifold Structured Prediction , 2018, NeurIPS.

[35]  Edwin R. Hancock,et al.  Spherical and Hyperbolic Embeddings of Data , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  M. Hamann On the tree-likeness of hyperbolic spaces , 2011, Mathematical Proceedings of the Cambridge Philosophical Society.

[37]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[38]  Silvere Bonnabel,et al.  Stochastic Gradient Descent on Riemannian Manifolds , 2011, IEEE Transactions on Automatic Control.

[39]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Tomas Mikolov,et al.  Bag of Tricks for Efficient Text Classification , 2016, EACL.

[41]  Douwe Kiela,et al.  Poincaré Embeddings for Learning Hierarchical Representations , 2017, NIPS.

[42]  Thomas Hofmann,et al.  Predicting Structured Data (Neural Information Processing) , 2007 .

[43]  Valentin Khrulkov,et al.  Hyperbolic Image Embeddings , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).