Schedule
This is the preliminary schedule of the workshop. All slots are provided in Central European Time (CET) and Eastern Standard Time (EST) using a 24h format. Use this time zone converter to convert these times to your local time zone.
The poster sessions and discussions will be live. Poster sessions take place in the Gather.Town instance of the workshop. Each poster listed for a specific session will have at least one of the authors available to answer any questions of participants. See below for a detailed breakdown of poster sessions.
| Time (CET) | Time (EST) | Event |
| 08:00–08:15 | 02:00–02:15 | Introduction |
| 08:15–08:45 | 02:15–02:45 | Keynote I: Kathryn Hess |
| 08:45–09:00 | 02:45–03:00 | Vidit Nanda |
| 09:00–09:15 | 03:00–03:15 | Yuzuru Yamakage |
| 09:15–09:30 | 03:15–03:30 | Katharine Turner |
| 09:30–09:45 | 03:30–03:45 | Manohar Kaul |
| 09:45–10:00 | 03:45–04:00 | Yasuaki Hiraoka |
| 10:00–10:15 | 04:00–04:15 | Serguei Barannikov |
| 10:15–10:30 | 04:15–04:30 | Ulrich Bauer |
| 10:30–11:15 | 04:30–05:15 | Poster Session I |
| 11:15–12:00 | 05:15–06:00 | Discussion I |
| 12:00–12:30 | 06:00–06:30 | Keynote II: Gunnar Carlsson |
| 12:30–13:00 | 06:30–07:00 | Break |
| 13:30–13:30 | 07:00–07:30 | Lida Kanari (live) |
| 13:30–13:45 | 07:30–07:45 | Peter Bubenik |
| 13:45–14:00 | 07:45–08:00 | Andrew J. Blumberg |
| 14:00–14:45 | 08:00–08:45 | Demo Session Teaspoon Package (live in Gather.Town) |
| 14:00–14:15 | 08:00–08:15 | Bei Wang |
| 14:15–14:30 | 08:15–08:30 | Lorin Crawford |
| 14:30–14:45 | 08:30–08:45 | Chao Chen |
| 14:45–15:30 | 08:45–09:30 | Demo Session giotto-tda (live in Gather.Town) |
| 14:45–15:00 | 08:45–09:00 | Mathieu Carrière |
| 15:00–15:15 | 09:00–09:15 | Brittany Terese Fasy |
| 15:15–15:30 | 09:15–09:30 | Don Sheehy |
| 15:30–16:15 | 09:30–10:15 | Poster Session II |
| 16:15–17:00 | 10:15–11:00 | Discussion II |
| 17:00–17:15 | 11:00–11:15 | Laxmi Parida |
| 17:15–17:30 | 11:15–11:30 | Jose Perea |
| 17:30–17:45 | 11:30–11:45 | Yusu Wang |
| 17:45–18:00 | 11:45–12:00 | Robert Ghrist |
| 18:00–18:15 | 12:00–12:15 | Elizabeth Munch |
| 18:15–18:30 | 12:15–12:30 | Leland McInnes |
| 18:30–18:45 | 12:30–12:45 | Facundo Mémoli |
| 18:45–19:30 | 12:45–13:30 | Poster Session III |
| 19:30–20:15 | 13:30–14:15 | Discussion III |
| 20:15–20:30 | 14:15–14:30 | Wrap-up |
Poster Session I
- $k$-simplex2vec: a simplicial extension of node2vec
- 0-dimensional Homology Preserving Dimensionality Reduction with TopoMap
- Application of Topological Data Analysis to Delirium Detection
- Cell Complex Neural Networks
- Challenging Euclidean Topological Autoencoders
- Deep Graph Mapper: Seeing Graphs Through the Neural Lens
- Fuzzy c-Means Clustering for Persistence Diagrams
- giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration
- Hotspot identification for Mapper graphs
- Hypothesis classes with a unique persistence diagram are nonuniformly learnable
- Interpretable Phase Detection and Classification with Persistent Homology
- Multi-parameter hierarchical clustering and beyond
- Multidimensional Persistence Module Classification via Lattice-Theoretic Convolutions
- On The Topological Expressive Power of Neural Networks
- Research Directions to Validate Topological Models of Multi-Dimensional Data
- Simplicial Neural Networks
- Teaspoon: A comprehensive python package for topological signal processing
- Topological Echoes of Primordial Physics in the Universe at Large Scales
Discussion I
This session will be live! Please use the Rocket.Chat on the NeurIPS workshop website or the Slack channel to ask your questions.
Participants in this panel
- Serguei Barannikov
- Ulrich Bauer
- Robert Ghrist
- Yasu Hiraoka
- Manohar Kaul
- Vidit Nanda
- Katharine Turner
- Yuzuru Yamakage
Poster Session II
- $k$-simplex2vec: a simplicial extension of node2vec
- Bifurcation Analysis using Zigzag Persistence
- Can neural networks learn persistent homology features?
- Challenging Euclidean Topological Autoencoders
- Characterizing the Latent Space of Molecular Deep Generative Models with Persistent Homology Metrics
- Functorial Clustering via Simplicial Complexes
- Fuzzy c-Means Clustering for Persistence Diagrams
- giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration
- Hypothesis classes with a unique persistence diagram are nonuniformly learnable
- Learning a manifold from a teacher’s demonstrations
- LUMAWIG: Un-bottling the bottleneck distance for zero dimensional persistence diagrams at scale
- Multi-Parameter Persistent Homology is Practical (Extended Abstract)
- Multiple Hypothesis Testing with Persistent Homology
- Novel Topological Shapes of Model Interpretability
- On The Topological Expressive Power of Neural Networks
- Permutation invariant networks to learn Wasserstein metrics
- Quantifying barley morphology using the Euler characteristic transform
- Regularization of Persistent Homology Gradient Computation
- Sheaf Neural Networks
- Simplicial Neural Networks
- Teaspoon: A comprehensive python package for topological signal processing
- Topo Sampler: A Topology Constrained Noise Sampling for GANs
- Topological Convolutional Neural Networks
- Using topological autoencoders as a filtering function for global and local topology
Discussion II
This session will be live! Please use the Rocket.Chat on the NeurIPS workshop website or the Slack channel to ask your questions.
Participants in this panel
- Serguei Barannikov
- Ulrich Bauer
- Andrew J. Blumberg
- Gunnar Carlsson
- Chao Chen
- Brittany Terese Fasy
- Kathryn Hess
- Lida Kanari
- Laxmi Parida
- Don Sheehy
- Bei Wang
- Yusu Wang
Poster Session III
- Bifurcation Analysis using Zigzag Persistence
- Can neural networks learn persistent homology features?
- Cell Complex Neural Networks
- Comparing Distance Metrics on Vectorized Persistence Summaries
- Fuzzy c-Means Clustering for Persistence Diagrams
- giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration
- Hypothesis classes with a unique persistence diagram are nonuniformly learnable
- Interpretable Phase Detection and Classification with Persistent Homology
- Learning a manifold from a teacher’s demonstrations
- Multi-Parameter Persistent Homology is Practical (Extended Abstract)
- On The Topological Expressive Power of Neural Networks
- Passive Encrypted IoT Device Fingerprinting with Persistent Homology
- Permutation invariant networks to learn Wasserstein metrics
- Quantifying barley morphology using the Euler characteristic transform
- Simplicial 2-Complex Convolutional Neural Networks
- Teaspoon: A comprehensive python package for topological signal processing
- TOTOPO: Classifying univariate and multivariate time series with Topological Data Analysis
- Using topological autoencoders as a filtering function for global and local topology
- Weighting vectors for machine learning: numerical harmonic analysis applied to boundary detection
- Witness Autoencoder: Shaping the Latent Space with Witness Complexes
Discussion III
This session will be live! Please use the Rocket.Chat on the NeurIPS workshop website or the Slack channel to ask your questions.