CubeRep: Learning Relations Between Different Views of Data

Rishi Sonthalia, Anna C. Gilbert, Matthew Durham
Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, PMLR 196:298-303, 2022.

Abstract

Multi-view learning tasks typically seek an aggregate synthesis of multiple views or perspectives of a single data set. The current approach assumes that there is an ambient space $X$ in which the views are images of $X$ under certain functions and attempts to learn these functions via a neural network. Unfortunately, such an approach neglects to consider the geometry of the ambient space. Hierarchically hyperbolic spaces (HHSes) do, however, provide a natural multi-view arrangement of data; they provide geometric tools for the assembly of different views of a single data set into a coherent global space, a \emph{CAT(0) cube complex}. In this work, we provide the first step toward theoretically justifiable methods for learning embeddings of multi-view data sets into CAT(0) cube complexes. We present an algorithm which, given a finite set of finite metric spaces (views) on a finite set of points (the objects), produces the key components of an HHS structure. From this structure, we can produce a \emph{CAT(0) cube complex} that encodes the hyperbolic geometry in the data while simultaneously allowing for Euclidean features given by the detected relations among the views.

Cite this Paper

BibTeX
@InProceedings{pmlr-v196-sonthalia22a, title = {CubeRep: Learning Relations Between Different Views of Data }, author = {Sonthalia, Rishi and Gilbert, Anna C. and Durham, Matthew}, booktitle = {Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022}, pages = {298--303}, year = {2022}, editor = {Cloninger, Alexander and Doster, Timothy and Emerson, Tegan and Kaul, Manohar and Ktena, Ira and Kvinge, Henry and Miolane, Nina and Rieck, Bastian and Tymochko, Sarah and Wolf, Guy}, volume = {196}, series = {Proceedings of Machine Learning Research}, month = {25 Feb--22 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v196/sonthalia22a/sonthalia22a.pdf}, url = {https://proceedings.mlr.press/v196/sonthalia22a.html}, abstract = {Multi-view learning tasks typically seek an aggregate synthesis of multiple views or perspectives of a single data set. The current approach assumes that there is an ambient space $X$ in which the views are images of $X$ under certain functions and attempts to learn these functions via a neural network. Unfortunately, such an approach neglects to consider the geometry of the ambient space. Hierarchically hyperbolic spaces (HHSes) do, however, provide a natural multi-view arrangement of data; they provide geometric tools for the assembly of different views of a single data set into a coherent global space, a \emph{CAT(0) cube complex}. In this work, we provide the first step toward theoretically justifiable methods for learning embeddings of multi-view data sets into CAT(0) cube complexes. We present an algorithm which, given a finite set of finite metric spaces (views) on a finite set of points (the objects), produces the key components of an HHS structure. From this structure, we can produce a \emph{CAT(0) cube complex} that encodes the hyperbolic geometry in the data while simultaneously allowing for Euclidean features given by the detected relations among the views.} }
Endnote
%0 Conference Paper %T CubeRep: Learning Relations Between Different Views of Data %A Rishi Sonthalia %A Anna C. Gilbert %A Matthew Durham %B Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022 %C Proceedings of Machine Learning Research %D 2022 %E Alexander Cloninger %E Timothy Doster %E Tegan Emerson %E Manohar Kaul %E Ira Ktena %E Henry Kvinge %E Nina Miolane %E Bastian Rieck %E Sarah Tymochko %E Guy Wolf %F pmlr-v196-sonthalia22a %I PMLR %P 298--303 %U https://proceedings.mlr.press/v196/sonthalia22a.html %V 196 %X Multi-view learning tasks typically seek an aggregate synthesis of multiple views or perspectives of a single data set. The current approach assumes that there is an ambient space $X$ in which the views are images of $X$ under certain functions and attempts to learn these functions via a neural network. Unfortunately, such an approach neglects to consider the geometry of the ambient space. Hierarchically hyperbolic spaces (HHSes) do, however, provide a natural multi-view arrangement of data; they provide geometric tools for the assembly of different views of a single data set into a coherent global space, a \emph{CAT(0) cube complex}. In this work, we provide the first step toward theoretically justifiable methods for learning embeddings of multi-view data sets into CAT(0) cube complexes. We present an algorithm which, given a finite set of finite metric spaces (views) on a finite set of points (the objects), produces the key components of an HHS structure. From this structure, we can produce a \emph{CAT(0) cube complex} that encodes the hyperbolic geometry in the data while simultaneously allowing for Euclidean features given by the detected relations among the views.
APA
Sonthalia, R., Gilbert, A.C. & Durham, M.. (2022). CubeRep: Learning Relations Between Different Views of Data . Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, in Proceedings of Machine Learning Research 196:298-303 Available from https://proceedings.mlr.press/v196/sonthalia22a.html.

Related Material