Workshop
Deep Generative Models and Downstream Applications
José Miguel Hernández-Lobato · Yingzhen Li · Yichuan Zhang · Cheng Zhang · Austin Tripp · Weiwei Pan · Oren Rippel
Tue 14 Dec, 6 a.m. PST
Deep generative models (DGMs) have become an important research branch in deep learning, including a broad family of methods such as variational autoencoders, generative adversarial networks, normalizing flows, energy based models and autoregressive models. Many of these methods have been shown to achieve state-of-the-art results in the generation of synthetic data of different types such as text, speech, images, music, molecules, etc. However, besides just generating synthetic data, DGMs are of particular relevance in many practical downstream applications. A few examples are imputation and acquisition of missing data, anomaly detection, data denoising, compressed sensing, data compression, image super-resolution, molecule optimization, interpretation of machine learning methods, identifying causal structures in data, generation of molecular structures, etc. However, at present, there seems to be a disconnection between researchers working on new DGM-based methods and researchers applying such methods to practical problems (like the ones mentioned above). This workshop aims to fill in this gap by bringing the two aforementioned communities together.
Schedule
Tue 6:00 a.m. - 6:10 a.m.
|
Opening remarks
(
Presentation
)
>
SlidesLive Video |
🔗 |
Tue 6:10 a.m. - 6:25 a.m.
|
Invited talk #1: Aapo Hyvärinen
(
Presentation
)
>
SlidesLive Video |
Aapo Hyvarinen 🔗 |
Tue 6:25 a.m. - 6:30 a.m.
|
Q&A Invited Talk #1
(
Q&A
)
>
|
🔗 |
Tue 6:30 a.m. - 6:45 a.m.
|
Invited talk #2: Finale Doshi-Velez
(
Presentation
)
>
SlidesLive Video |
Finale Doshi-Velez 🔗 |
Tue 6:45 a.m. - 6:50 a.m.
|
Q&A Invited Talk #2
(
Q&A
)
>
|
🔗 |
Tue 6:50 a.m. - 7:05 a.m.
|
Invited Talk #3: Rianne van den Berg
(
Presentation
)
>
SlidesLive Video |
Rianne van den Berg 🔗 |
Tue 7:05 a.m. - 7:10 a.m.
|
Q&A Invited Talk #3
(
Q&A
)
>
|
🔗 |
Tue 7:10 a.m. - 7:20 a.m.
|
Particle Dynamics for Learning EBMs
(
Oral
)
>
link
SlidesLive Video |
Kirill Neklyudov · Priyank Jaini · Max Welling 🔗 |
Tue 7:20 a.m. - 7:30 a.m.
|
VAEs meet Diffusion Models: Efficient and High-Fidelity Generation
(
Oral
)
>
link
SlidesLive Video |
Kushagra Pandey · Avideep Mukherjee · Piyush Rai · Abhishek Kumar 🔗 |
Tue 7:30 a.m. - 7:35 a.m.
|
Contributed poster talk #1-2 Q&A
(
Q&A
)
>
|
🔗 |
Tue 7:35 a.m. - 8:00 a.m.
|
Break #1
|
🔗 |
Tue 8:00 a.m. - 8:15 a.m.
|
Invited talk #4: Chris Williams
(
Presentation
)
>
SlidesLive Video |
Chris Williams 🔗 |
Tue 8:15 a.m. - 8:20 a.m.
|
Q&A Invited Talk #4
(
Q&A
)
>
|
🔗 |
Tue 8:20 a.m. - 8:35 a.m.
|
Invited talk #5: Mihaela van der Schaar
(
Presentation
)
>
SlidesLive Video |
Mihaela van der Schaar 🔗 |
Tue 8:35 a.m. - 8:40 a.m.
|
Q&A Invited Talk #5
(
Q&A
)
>
|
🔗 |
Tue 8:40 a.m. - 8:55 a.m.
|
Invited Talk #6: Luisa Zintgraf
(
Presentation
)
>
SlidesLive Video |
Luisa Zintgraf 🔗 |
Tue 8:55 a.m. - 9:00 a.m.
|
Q&A Invited Talk #6
(
Q&A
)
>
|
🔗 |
Tue 9:00 a.m. - 9:10 a.m.
|
Your Dataset is a Multiset and You Should Compress it Like One
(
Oral
)
>
link
SlidesLive Video |
Daniel Severo · James Townsend · Ashish Khisti · Alireza Makhzani · Karen Ullrich 🔗 |
Tue 9:10 a.m. - 9:20 a.m.
|
Contributed poster talk #3 Q&A + Best paper awards
(
Q&A
)
>
SlidesLive Video |
🔗 |
Tue 9:20 a.m. - 10:00 a.m.
|
Break #2
|
🔗 |
Tue 10:00 a.m. - 11:00 a.m.
|
Poster session #1
(
poster session (gathertown)
)
>
|
🔗 |
Tue 11:00 a.m. - 11:30 a.m.
|
Panel Discussion
(
Discussion Panel
)
>
SlidesLive Video |
🔗 |
Tue 11:30 a.m. - 11:45 a.m.
|
Invited Talk #7: Romain Lopez
(
Presentation
)
>
SlidesLive Video |
Romain Lopez 🔗 |
Tue 11:45 a.m. - 11:50 a.m.
|
Q&A Invited Talk #7
(
Q&A
)
>
|
🔗 |
Tue 11:50 a.m. - 12:10 p.m.
|
Break #3
|
🔗 |
Tue 12:10 p.m. - 12:25 p.m.
|
Invited talk #8: Alex Anderson
(
Presentation
)
>
SlidesLive Video |
Alex Anderson 🔗 |
Tue 12:25 p.m. - 12:30 p.m.
|
Q&A Invited Talk #8
(
Q&A
)
>
|
🔗 |
Tue 12:30 p.m. - 12:40 p.m.
|
AGE: Enhancing the Convergence on GANs using Alternating extra-gradient with Gradient Extrapolation
(
Oral
)
>
link
SlidesLive Video |
Huan He · Shifan Zhao · Yuanzhe Xi · Joyce Ho 🔗 |
Tue 12:40 p.m. - 12:50 p.m.
|
Sample-Efficient Generation of Novel Photo-acid Generator Molecules using a Deep Generative Model
(
Oral
)
>
link
SlidesLive Video |
Samuel Hoffman · Vijil Chenthamarakshan · Dmitry Zubarev · Daniel Sanders · Payel Das 🔗 |
Tue 12:50 p.m. - 12:55 p.m.
|
Contributed poster talk #5-6 Q&A
(
Q&A
)
>
|
🔗 |
Tue 12:55 p.m. - 1:10 p.m.
|
Invited talk #9: Zhifeng Kong
(
Presentation
)
>
SlidesLive Video |
Zhifeng Kong 🔗 |
Tue 1:10 p.m. - 1:15 p.m.
|
Q&A Invited Talk #9
(
Q&A
)
>
|
🔗 |
Tue 1:15 p.m. - 1:30 p.m.
|
Invited talk #10: Johannes Ballé
(
Presentation
)
>
SlidesLive Video |
Johannes Ballé 🔗 |
Tue 1:30 p.m. - 1:35 p.m.
|
Q&A Invited Talk #10
(
Q&A
)
>
|
🔗 |
Tue 1:35 p.m. - 1:45 p.m.
|
Bayesian Image Reconstruction using Deep Generative Models
(
Oral
)
>
link
SlidesLive Video |
Razvan Marinescu · Daniel Moyer · Polina Golland 🔗 |
Tue 1:45 p.m. - 1:55 p.m.
|
Grapher: Multi-Stage Knowledge Graph Construction using Pretrained Language Models
(
Oral
)
>
link
SlidesLive Video |
Igor Melnyk · Pierre Dognin · Payel Das 🔗 |
Tue 1:55 p.m. - 2:00 p.m.
|
Contributed poster talk #7-8 Q&A
(
Q&A
)
>
|
🔗 |
Tue 2:00 p.m. - 3:00 p.m.
|
Poster session #2
(
poster session (gathertown)
)
>
|
🔗 |
-
|
Transparent Liquid Segmentation for Robotic Pouring ( Poster ) > link | Gautham Narayan Narasimhan · Kai Zhang · Benjamin Eisner · Xingyu Lin · David Held 🔗 |
-
|
Uncertainty-aware Labelled Augmentations for High Dimensional Latent Space Bayesian Optimization ( Poster ) > link | Ekansh Verma · Souradip Chakraborty 🔗 |
-
|
How to Reward Your Drug Agent? ( Poster ) > link | Andrea Karlova · Wim Dehaen · Andrei Penciu 🔗 |
-
|
Searching for the Weirdest Stars: A Convolutional Autoencoder-Based Pipeline For Detecting Anomalous Periodic Variable Stars ( Poster ) > link | Ho-Sang Chan · Siu Hei Cheung · Victoria Villar · Shirley Ho 🔗 |
-
|
XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches ( Poster ) > link | V Manushree · Sameer Saxena · Parna Chowdhury · Manisimha Varma Manthena · Harsh Rathod · Ankita Ghosh · Sahil Khose 🔗 |
-
|
Conditional Generation of Periodic Signals with Fourier-Based Decoder ( Poster ) > link | Jiyoung Lee · Wonjae Kim · DAEHOON GWAK · Edward Choi 🔗 |
-
|
Palette: Image-to-Image Diffusion Models ( Poster ) > link | Chitwan Saharia · William Chan · Huiwen Chang · Chris Lee · Jonathan Ho · Tim Salimans · David Fleet · Mohammad Norouzi 🔗 |
-
|
Semi-supervised Multiple Instance Learning using Variational Auto-Encoders ( Poster ) > link | Ali Nihat Uzunalioglu · Tameem Adel · Jakub M. Tomczak 🔗 |
-
|
Variational Autoencoder with Differentiable Physics Engine for Human Gait Analysis and Synthesis ( Poster ) > link | Naoya Takeishi · Alexandros Kalousis 🔗 |
-
|
A Binded VAE for Inorganic Material Generation ( Poster ) > link | Fouad OUBARI · Antoine De mathelin · Rodrigue Décatoire · Mathilde MOUGEOT 🔗 |
-
|
Certifiably Robust Variational Autoencoders ( Poster ) > link | Ben Barrett · Alexander Camuto · Matthew Willetts · Thomas Rainforth 🔗 |
-
|
Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration ( Poster ) > link | Si-An Chen · Chun-Liang Li · Hsuan-Tien Lin 🔗 |
-
|
Instance Semantic Segmentation Benefits from Generative Adversarial Networks ( Poster ) > link | Quang Le · KAMAL YOUCEF-TOUMI · Dzmitry Tsetserukou · Ali Jahanian 🔗 |
-
|
Classifier-Free Diffusion Guidance ( Poster ) > link | Jonathan Ho · Tim Salimans 🔗 |
-
|
Accurate Imputation and Efficient Data Acquisitionwith Transformer-based VAEs ( Poster ) > link | Sarah Lewis · Tatiana Matejovicova · Yingzhen Li · Angus Lamb · Yordan Zaykov · Miltiadis Allamanis · Cheng Zhang 🔗 |
-
|
Probabilistic Hierarchical Forecasting with Deep Poisson Mixtures ( Poster ) > link | Kin Olivares · Oinam Nganba Meetei · Ruijun Ma · Rohan Reddy · Mengfei Cao 🔗 |
-
|
Deep Generative model with Hierarchical Latent Factors for Timeseries Anomaly Detection ( Poster ) > link | Cristian Challu · Peihong Jiang · Ying Nian Wu · Laurent Callot 🔗 |
-
|
Entropic Issues in Likelihood-Based OOD Detection ( Poster ) > link | Anthony Caterini · Gabriel Loaiza-Ganem 🔗 |
-
|
Single Image Super-Resolution with Uncertainty Estimation for Lunar Satellite Images ( Poster ) > link | Jose Delgado-Centeno · Paula Harder · Ben Moseley · Valentin Bickel · Siddha Ganju · Miguel Olivares · Alfredo Kalaitzis 🔗 |
-
|
Self-Supervised Anomaly Detection via Neural Autoregressive Flows with Active Learning ( Poster ) > link | Jiaxin Zhang · Kyle Saleeby · Thomas Feldhausen · Sirui Bi · Alex Plotkowski · David Womble 🔗 |
-
|
Content-Based Image Retrieval from Weakly-Supervised Disentangled Representations ( Poster ) > link | Luis Armando Pérez Rey · Dmitri Jarnikov · Mike Holenderski 🔗 |
-
|
Deep Variational Semi-Supervised Novelty Detection ( Poster ) > link | Tal Daniel · Thanard Kurutach · Aviv Tamar 🔗 |
-
|
Controllable Network Data Balancing With GANs ( Poster ) > link | Fares Meghdouri · Thomas Schmied · Thomas Gaertner · Tanja Zseby 🔗 |
-
|
A Generalized and Distributable Generative Model for Private Representation Learning ( Poster ) > link | Sheikh Shams Azam · Taejin Kim · Seyyedali Hosseinalipour · Carlee Joe-Wong · Saurabh Bagchi · Christopher Brinton 🔗 |
-
|
Score-Based Generative Classifiers ( Poster ) > link | Roland S. Zimmermann · Lukas Schott · Yang Song · Benjamin Dunn · David Klindt 🔗 |
-
|
An Interpretability-augmented Genetic Expert for Deep Molecular Optimization ( Poster ) > link | Pierre Wüthrich · Jun Jin Choong · Shinya Yuki 🔗 |
-
|
Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination ( Poster ) > link | Jongmin Yu · Hyeontaek Oh · Minkyung Kim · Junsik Kim 🔗 |
-
|
Preventing posterior collapse in variational autoencoders for text generation via decoder regularization ( Poster ) > link | Alban Petit · Caio Corro 🔗 |
-
|
Latent Space Refinement for Deep Generative Models ( Poster ) > link | Ramon Winterhalder · Marco Bellagente · Benjamin Nachman 🔗 |
-
|
Stochastic Video Prediction with Perceptual Loss ( Poster ) > link | Donghun Lee · Ingook Jang · Seonghyun Kim · Chanwon Park · JUN HEE PARK 🔗 |
-
|
Few-Shot Out-of-Domain Transfer of Natural Language Explanations ( Poster ) > link | Yordan Yordanov · Vid Kocijan · Thomas Lukasiewicz · Oana M Camburu 🔗 |
-
|
Learning Disentangled Representation for Spatiotemporal Graph Generation ( Poster ) > link | Yuanqi Du · Xiaojie Guo · Hengning Cao · Yanfang (Fa Ye · Liang Zhao 🔗 |
-
|
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification ( Poster ) > link | Junwen Bai · Shufeng Kong · Carla Gomes 🔗 |
-
|
Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation ( Poster ) > link | Tobias Weber · Michael Ingrisch · Bernd Bischl · David Rügamer 🔗 |
-
|
Finding Maximally Informative Patches in Images ( Poster ) > link | Howard Zhong · Guha Balakrishnan · Richard Bowen · Ramin Zabih · Bill Freeman 🔗 |
-
|
Accurate Imputation and Efficient Data Acquisitionwith Transformer-based VAEs ( Oral ) > link | Sarah Lewis · Tatiana Matejovicova · Yingzhen Li · Angus Lamb · Yordan Zaykov · Miltiadis Allamanis · Cheng Zhang 🔗 |
-
|
AGE: Enhancing the Convergence on GANs using Alternating extra-gradient with Gradient Extrapolation ( Poster ) > link | Huan He · Shifan Zhao · Yuanzhe Xi · Joyce Ho 🔗 |
-
|
How to Reward Your Drug Agent? ( Oral ) > link | Andrea Karlova · Wim Dehaen · Andrei Penciu 🔗 |
-
|
VAEs meet Diffusion Models: Efficient and High-Fidelity Generation ( Poster ) > link | Kushagra Pandey · Avideep Mukherjee · Piyush Rai · Abhishek Kumar 🔗 |
-
|
Content-Based Image Retrieval from Weakly-Supervised Disentangled Representations ( Oral ) > link | Luis Armando Pérez Rey · Dmitri Jarnikov · Mike Holenderski 🔗 |
-
|
Classifier-Free Diffusion Guidance ( Oral ) > link | Jonathan Ho · Tim Salimans 🔗 |
-
|
Bayesian Image Reconstruction using Deep Generative Models ( Poster ) > link | Razvan Marinescu · Daniel Moyer · Polina Golland 🔗 |
-
|
Searching for the Weirdest Stars: A Convolutional Autoencoder-Based Pipeline For Detecting Anomalous Periodic Variable Stars ( Oral ) > link | Ho-Sang Chan · Siu Hei Cheung · Victoria Villar · Shirley Ho 🔗 |
-
|
Your Dataset is a Multiset and You Should Compress it Like One ( Poster ) > link | Daniel Severo · James Townsend · Ashish Khisti · Alireza Makhzani · Karen Ullrich 🔗 |
-
|
Probabilistic Hierarchical Forecasting with Deep Poisson Mixtures ( Oral ) > link | Kin Olivares · Oinam Nganba Meetei · Ruijun Ma · Rohan Reddy · Mengfei Cao 🔗 |
-
|
Uncertainty-aware Labelled Augmentations for High Dimensional Latent Space Bayesian Optimization ( Oral ) > link | Ekansh Verma · Souradip Chakraborty 🔗 |
-
|
A Binded VAE for Inorganic Material Generation ( Oral ) > link | Fouad OUBARI · Antoine De mathelin · Rodrigue Décatoire · Mathilde MOUGEOT 🔗 |
-
|
Controllable Network Data Balancing With GANs ( Oral ) > link | Fares Meghdouri · Thomas Schmied · Thomas Gaertner · Tanja Zseby 🔗 |
-
|
Palette: Image-to-Image Diffusion Models ( Oral ) > link | Chitwan Saharia · William Chan · Huiwen Chang · Chris Lee · Jonathan Ho · Tim Salimans · David Fleet · Mohammad Norouzi 🔗 |
-
|
Stochastic Video Prediction with Perceptual Loss ( Oral ) > link | Donghun Lee · Ingook Jang · Seonghyun Kim · Chanwon Park · JUN HEE PARK 🔗 |
-
|
Particle Dynamics for Learning EBMs ( Poster ) > link | Kirill Neklyudov · Priyank Jaini · Max Welling 🔗 |
-
|
Instance Semantic Segmentation Benefits from Generative Adversarial Networks ( Oral ) > link | Quang Le · KAMAL YOUCEF-TOUMI · Dzmitry Tsetserukou · Ali Jahanian 🔗 |
-
|
Sample-Efficient Generation of Novel Photo-acid Generator Molecules using a Deep Generative Model ( Poster ) > link | Samuel Hoffman · Vijil Chenthamarakshan · Dmitry Zubarev · Daniel Sanders · Payel Das 🔗 |
-
|
Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations ( Oral ) > link | Jan Zuiderveld · Marco Federici · Erik Bekkers 🔗 |
-
|
Conditional Generation of Periodic Signals with Fourier-Based Decoder ( Oral ) > link | Jiyoung Lee · Wonjae Kim · DAEHOON GWAK · Edward Choi 🔗 |
-
|
Finding Maximally Informative Patches in Images ( Oral ) > link | Howard Zhong · Guha Balakrishnan · Richard Bowen · Ramin Zabih · Bill Freeman 🔗 |
-
|
Preventing posterior collapse in variational autoencoders for text generation via decoder regularization ( Oral ) > link | Alban Petit · Caio Corro 🔗 |
-
|
An Interpretability-augmented Genetic Expert for Deep Molecular Optimization ( Oral ) > link | Pierre Wüthrich · Jun Jin Choong · Shinya Yuki 🔗 |
-
|
Deep Generative model with Hierarchical Latent Factors for Timeseries Anomaly Detection ( Oral ) > link | Cristian Challu · Peihong Jiang · Ying Nian Wu · Laurent Callot 🔗 |
-
|
XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches ( Oral ) > link | V Manushree · Sameer Saxena · Parna Chowdhury · Manisimha Varma Manthena · Harsh Rathod · Ankita Ghosh · Sahil Khose 🔗 |
-
|
Variational Autoencoder with Differentiable Physics Engine for Human Gait Analysis and Synthesis ( Oral ) > link | Naoya Takeishi · Alexandros Kalousis 🔗 |
-
|
Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation ( Oral ) > link | Tobias Weber · Michael Ingrisch · Bernd Bischl · David Rügamer 🔗 |
-
|
A Generalized and Distributable Generative Model for Private Representation Learning ( Oral ) > link | Sheikh Shams Azam · Taejin Kim · Seyyedali Hosseinalipour · Carlee Joe-Wong · Saurabh Bagchi · Christopher Brinton 🔗 |
-
|
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification ( Oral ) > link | Junwen Bai · Shufeng Kong · Carla Gomes 🔗 |
-
|
Deep Variational Semi-Supervised Novelty Detection ( Oral ) > link | Tal Daniel · Thanard Kurutach · Aviv Tamar 🔗 |
-
|
Latent Space Refinement for Deep Generative Models ( Oral ) > link | Ramon Winterhalder · Marco Bellagente · Benjamin Nachman 🔗 |
-
|
Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration ( Oral ) > link | Si-An Chen · Chun-Liang Li · Hsuan-Tien Lin 🔗 |
-
|
Learning Disentangled Representation for Spatiotemporal Graph Generation ( Oral ) > link | Yuanqi Du · Xiaojie Guo · Hengning Cao · Yanfang (Fa Ye · Liang Zhao 🔗 |
-
|
Score-Based Generative Classifiers ( Oral ) > link | Roland S. Zimmermann · Lukas Schott · Yang Song · Benjamin Dunn · David Klindt 🔗 |
-
|
Transparent Liquid Segmentation for Robotic Pouring ( Oral ) > link | Gautham Narayan Narasimhan · Kai Zhang · Benjamin Eisner · Xingyu Lin · David Held 🔗 |
-
|
Grapher: Multi-Stage Knowledge Graph Construction using Pretrained Language Models ( Poster ) > link | Igor Melnyk · Pierre Dognin · Payel Das 🔗 |
-
|
Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination ( Oral ) > link | Jongmin Yu · Hyeontaek Oh · Minkyung Kim · Junsik Kim 🔗 |
-
|
Self-Supervised Anomaly Detection via Neural Autoregressive Flows with Active Learning ( Oral ) > link | Jiaxin Zhang · Kyle Saleeby · Thomas Feldhausen · Sirui Bi · Alex Plotkowski · David Womble 🔗 |
-
|
Semi-supervised Multiple Instance Learning using Variational Auto-Encoders ( Oral ) > link | Ali Nihat Uzunalioglu · Tameem Adel · Jakub M. Tomczak 🔗 |
-
|
Certifiably Robust Variational Autoencoders ( Oral ) > link | Ben Barrett · Alexander Camuto · Matthew Willetts · Thomas Rainforth 🔗 |
-
|
Entropic Issues in Likelihood-Based OOD Detection ( Oral ) > link | Anthony Caterini · Gabriel Loaiza-Ganem 🔗 |
-
|
Single Image Super-Resolution with Uncertainty Estimation for Lunar Satellite Images ( Oral ) > link | Jose Delgado-Centeno · Paula Harder · Ben Moseley · Valentin Bickel · Siddha Ganju · Miguel Olivares · Alfredo Kalaitzis 🔗 |
-
|
Few-Shot Out-of-Domain Transfer of Natural Language Explanations ( Oral ) > link | Yordan Yordanov · Vid Kocijan · Thomas Lukasiewicz · Oana M Camburu 🔗 |
-
|
Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations
(
Poster
)
>
|
🔗 |