This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

Workshop: Differential Geometry meets Deep Learning (DiffGeo4DL)

Joey Bose, Emile Mathieu, Charline Le Lan, Ines Chami, Fred Sala, Christopher De Sa, Maximillian Nickel, Chris Ré, Will Hamilton

2020-12-11T05:45:00-08:00 - 2020-12-11T14:00:00-08:00
Abstract: Recent years have seen a surge in research at the intersection of differential geometry and deep learning, including techniques for stochastic optimization on curved spaces (e.g., hyperbolic or spherical manifolds), learning embeddings for non-Euclidean data, and generative modeling on Riemannian manifolds. Insights from differential geometry have led to new state of the art approaches to modeling complex real world data, such as graphs with hierarchical structure, 3D medical data, and meshes.
Thus, it is of critical importance to understand, from a geometric lens, the natural invariances, equivariances, and symmetries that reside within data.

In order to support the burgeoning interest of differential geometry in deep learning, the primary goal for this workshop is to facilitate community building and to work towards the identification of key challenges in comparison with regular deep learning, along with techniques to overcome these challenges. With many new researchers beginning projects in this area, we hope to bring them together to consolidate this fast-growing area into a healthy and vibrant subfield. In particular, we aim to strongly promote novel and exciting applications of differential geometry for deep learning with an emphasis on bridging theory to practice which is reflected in our choices of invited speakers, which include both machine learning practitioners and researchers who are primarily geometers.


To ask questions please use rocketchat, available only upon registration and login.


2020-12-11T05:00:00-08:00 - 2020-12-11T15:00:00-08:00
2020-12-11T05:45:00-08:00 - 2020-12-11T06:00:00-08:00
Opening Remarks
Joey Bose
2020-12-11T06:00:00-08:00 - 2020-12-11T06:30:00-08:00
Invited Talk 1: Geometric deep learning for 3D human body synthesis
Michael Bronstein
2020-12-11T06:30:00-08:00 - 2020-12-11T07:00:00-08:00
Invited Talk 2: Gauge Theory in Geometric Deep Learning
Taco Cohen
2020-12-11T07:00:00-08:00 - 2020-12-11T07:05:00-08:00
Contributed Talk 1: Learning Hyperbolic Representations for Unsupervised 3D Segmentation
Joy Hsu, Jeffrey Gu, Serena Yeung
2020-12-11T07:06:00-08:00 - 2020-12-11T07:11:00-08:00
Contributed Talk 2: Witness Autoencoder: Shaping the Latent Space with Witness Complexes
Anastasiia Varava, Danica Kragic, Simon Schönenberger, Vladislav Polianskii , Jen Jen Chung, Vladislav Polianskii
2020-12-11T07:12:00-08:00 - 2020-12-11T07:17:00-08:00
Contributed Talk 3: A Riemannian gradient flow perspective on learning deep linear neural networks
Ulrich Terstiege, Holger Rauhut, Bubacarr Bah, Michael Westdickenberg
2020-12-11T07:18:00-08:00 - 2020-12-11T07:23:00-08:00
Contributed Talk 4: Directional Graph Networks
Dominique Beaini, Saro Passaro, Vincent Létourneau, Will Hamilton, Gabriele Corso, Pietro Liò
2020-12-11T07:24:00-08:00 - 2020-12-11T07:29:00-08:00
Contributed Talk 5: A New Neural Network Architecture Invariant to the Action of Symmetry Subgroups
Mete Ozay, Piotr Kicki, Piotr Skrzypczynski
2020-12-11T07:30:00-08:00 - 2020-12-11T08:00:00-08:00
Virtual Coffee Break on Gather.Town
2020-12-11T08:00:00-08:00 - 2020-12-11T08:30:00-08:00
Invited Talk 3: Reparametrization invariance in representation learning
Søren Hauberg
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
Graph of Thrones : Adversarial Perturbations dismantle Aristocracy in Graphs
Adarsh Jamadandi, Uma Mudenagudi
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
Hermitian Symmetric Spaces for Graph Embeddings
Federico Lopez, Beatrice Pozzetti, Steve Trettel, Anna Wienhard
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
Quaternion Graph Neural Networks
Dai Quoc Nguyen, Tu Dinh Nguyen, Dinh Phung
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
Grassmann Iterative Linear Discriminant Analysis with Proxy Matrix Optimization
Navya Nagananda, Breton Minnehan, Andreas Savakis
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
A Metric for Linear Symmetry-Based Disentanglement
Luis Armando Pérez Rey, Loek Tonnaer, Vlado Menkovski, Mike Holenderski, Jim Portegies
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
Poster Session 1 on Gather.Town
Joey Bose, Ines Chami
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
Tree Covers: An Alternative to Metric Embeddings
Roshni Sahoo, Ines Chami, Christopher Ré
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
Deep Networks and the Multiple Manifold Problem
Sam Buchanan, Dar Gilboa, John Wright
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
Isometric Gaussian Process Latent Variable Model
Martin Jørgensen, Søren Hauberg
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
Universal Approximation Property of Neural Ordinary Differential Equations
Takeshi Teshima, Koichi Tojo, Masahiro Ikeda, Isao Ishikawa, Kenta Oono
2020-12-11T08:30:00-08:00 - 2020-12-11T09:30:00-08:00
GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability
Arinbjörn Kolbeinsson, Nicholas Jennings, Marc Deisenroth, Daniel Lengyel, Janith Petangoda, Michalis Lazarou, Kate Highnam, John Falk
2020-12-11T09:30:00-08:00 - 2020-12-11T10:15:00-08:00
Panel Discussion
Joey Bose, Emile Mathieu, Charline Le Lan, Ines Chami
2020-12-11T10:15:00-08:00 - 2020-12-11T10:45:00-08:00
Virtual Coffee Break on Gather.Town
2020-12-11T10:45:00-08:00 - 2020-12-11T11:30:00-08:00
Focused Breakout Session
Ines Chami, Joey Bose
2020-12-11T11:30:00-08:00 - 2020-12-11T12:00:00-08:00
Invited Talk 4: An introduction to the Calderon and Steklov inverse problems on Riemannian manifolds with boundary
Niky Kamran
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Poster Session 2 on Gather.Town
Charline Le Lan, Emile Mathieu
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Towards Geometric Understanding of Low-Rank Approximation
Mahito Sugiyama, Kazu Ghalamkari
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
The Intrinsic Dimension of Images and Its Impact on Learning
Chen Zhu, Micah Goldblum, Ahmed Abdelkader, Tom Goldstein, Phillip Pope
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Extendable and invertible manifold learning with geometry regularized autoencoders
Andres F Duque, Sacha Morin, Guy Wolf, Kevin Moon
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Convex Optimization for Blind Source Separation on a Statistical Manifold
Simon Luo, lamiae azizi, Mahito Sugiyama
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Sparsifying networks by traversing Geodesics
Guruprasad Raghavan, Matt Thomson
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
QuatRE: Relation-Aware Quaternions for Knowledge Graph Embeddings
Dai Quoc Nguyen, Dinh Phung
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Leveraging Smooth Manifolds for Lexical Semantic Change Detection across Corpora
Anmol Goel, Ponnurangam Kumaraguru
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Unsupervised Orientation Learning Using Autoencoders
Rembert Daems, Francis Wyffels
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Deep Riemannian Manifold Learning
Aaron Lou, Maximillian Nickel, Brandon Amos
2020-12-11T12:00:00-08:00 - 2020-12-11T13:00:00-08:00
Affinity guided Geometric Semi-Supervised Metric Learning
Ujjal Dutta, Mehrtash Harandi, C Chandra Shekhar
2020-12-11T13:00:00-08:00 - 2020-12-11T13:30:00-08:00
Invited Talk 5: Disentangling Orientation and Camera Parameters from Cryo-Electron Microscopy Images Using Differential Geometry and Variational Autoencoders
Nina Miolane
2020-12-11T13:30:00-08:00 - 2020-12-11T14:00:00-08:00
Invited Talk 6: Learning a robust classifier in hyperbolic space
Melanie Weber