( events)   Timezone: »  
Workshop
Tue Dec 14 06:00 AM -- 03:00 PM (PST)
Deep Generative Models and Downstream Applications
Jose Miguel Hernández-Lobato · Yingzhen Li · Yichuan Zhang · Cheng Zhang · Austin Tripp · Weiwei Pan · Oren Rippel





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.

Opening remarks (Presentation)
Invited talk #1: Aapo Hyvärinen (Presentation)
Q&A Invited Talk #1 (Q&A)
Invited talk #2: Finale Doshi-Velez (Presentation)
Q&A Invited Talk #2 (Q&A)
Invited Talk #3: Rianne van den Berg (Presentation)
Q&A Invited Talk #3 (Q&A)
Particle Dynamics for Learning EBMs (Oral)
VAEs meet Diffusion Models: Efficient and High-Fidelity Generation (Oral)
Contributed poster talk #1-2 Q&A (Q&A)
Break #1 (Break)
Invited talk #4: Chris Williams (Presentation)
Q&A Invited Talk #4 (Q&A)
Invited talk #5: Mihaela van der Schaar (Presentation)
Q&A Invited Talk #5 (Q&A)
Invited Talk #6: Luisa Zintgraf (Presentation)
Q&A Invited Talk #6 (Q&A)
Your Dataset is a Multiset and You Should Compress it Like One (Oral)
Contributed poster talk #3 Q&A + Best paper awards (Q&A)
Break #2 (Break)
Poster session #1 (poster session (gathertown))
Panel Discussion (Discussion Panel)
Invited Talk #7: Romain Lopez (Presentation)
Q&A Invited Talk #7 (Q&A)
Break #3 (Break)
Invited talk #8: Alex Anderson (Presentation)
Q&A Invited Talk #8 (Q&A)
AGE: Enhancing the Convergence on GANs using Alternating extra-gradient with Gradient Extrapolation (Oral)
Sample-Efficient Generation of Novel Photo-acid Generator Molecules using a Deep Generative Model (Oral)
Contributed poster talk #5-6 Q&A (Q&A)
Invited talk #9: Zhifeng Kong (Presentation)
Q&A Invited Talk #9 (Q&A)
Invited talk #10: Johannes Ballé (Presentation)
Q&A Invited Talk #10 (Q&A)
Bayesian Image Reconstruction using Deep Generative Models (Oral)
Grapher: Multi-Stage Knowledge Graph Construction using Pretrained Language Models (Oral)
Contributed poster talk #7-8 Q&A (Q&A)
Poster session #2 (poster session (gathertown))
Content-Based Image Retrieval from Weakly-Supervised Disentangled Representations (Poster)
Particle Dynamics for Learning EBMs (Poster)
Probabilistic Hierarchical Forecasting with Deep Poisson Mixtures (Poster)
Bayesian Image Reconstruction using Deep Generative Models (Poster)
AGE: Enhancing the Convergence on GANs using Alternating extra-gradient with Gradient Extrapolation (Poster)
VAEs meet Diffusion Models: Efficient and High-Fidelity Generation (Poster)
Finding Maximally Informative Patches in Images (Poster)
Learning Disentangled Representation for Spatiotemporal Graph Generation (Poster)
Score-Based Generative Classifiers (Poster)
Entropic Issues in Likelihood-Based OOD Detection (Poster)
A Binded VAE for Inorganic Material Generation (Poster)
Variational Autoencoder with Differentiable Physics Engine for Human Gait Analysis and Synthesis (Poster)
Semi-supervised Multiple Instance Learning using Variational Auto-Encoders (Poster)
Palette: Image-to-Image Diffusion Models (Poster)
How to Reward Your Drug Agent? (Poster)
A Binded VAE for Inorganic Material Generation (Oral)
Transparent Liquid Segmentation for Robotic Pouring (Oral)
Instance Semantic Segmentation Benefits from Generative Adversarial Networks (Poster)
Preventing posterior collapse in variational autoencoders for text generation via decoder regularization (Oral)
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification (Poster)
XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches (Oral)
Searching for the Weirdest Stars: A Convolutional Autoencoder-Based Pipeline For Detecting Anomalous Periodic Variable Stars (Oral)
Semi-supervised Multiple Instance Learning using Variational Auto-Encoders (Oral)
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification (Oral)
A Generalized and Distributable Generative Model for Private Representation Learning (Poster)
Learning Disentangled Representation for Spatiotemporal Graph Generation (Oral)
Single Image Super-Resolution with Uncertainty Estimation for Lunar Satellite Images (Oral)
Few-Shot Out-of-Domain Transfer of Natural Language Explanations (Oral)
Stochastic Video Prediction with Perceptual Loss (Oral)
XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches (Poster)
Few-Shot Out-of-Domain Transfer of Natural Language Explanations (Poster)
Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations (Poster)
Accurate Imputation and Efficient Data Acquisitionwith Transformer-based VAEs (Poster)
Grapher: Multi-Stage Knowledge Graph Construction using Pretrained Language Models (Poster)
Preventing posterior collapse in variational autoencoders for text generation via decoder regularization (Poster)
Conditional Generation of Periodic Signals with Fourier-Based Decoder (Oral)
Controllable Network Data Balancing With GANs (Oral)
Controllable Network Data Balancing With GANs (Poster)
Finding Maximally Informative Patches in Images (Oral)
Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration (Oral)
Certifiably Robust Variational Autoencoders (Oral)
Deep Variational Semi-Supervised Novelty Detection (Poster)
Stochastic Video Prediction with Perceptual Loss (Poster)
Self-Supervised Anomaly Detection via Neural Autoregressive Flows with Active Learning (Poster)
Palette: Image-to-Image Diffusion Models (Oral)
Deep Generative model with Hierarchical Latent Factors for Timeseries Anomaly Detection (Oral)
An Interpretability-augmented Genetic Expert for Deep Molecular Optimization (Oral)
Score-Based Generative Classifiers (Oral)
Uncertainty-aware Labelled Augmentations for High Dimensional Latent Space Bayesian Optimization (Oral)
Instance Semantic Segmentation Benefits from Generative Adversarial Networks (Oral)
Variational Autoencoder with Differentiable Physics Engine for Human Gait Analysis and Synthesis (Oral)
Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation (Oral)
A Generalized and Distributable Generative Model for Private Representation Learning (Oral)
Deep Variational Semi-Supervised Novelty Detection (Oral)
Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination (Oral)
Classifier-Free Diffusion Guidance (Oral)
Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations (Oral)
Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination (Poster)
Deep Generative model with Hierarchical Latent Factors for Timeseries Anomaly Detection (Poster)
Classifier-Free Diffusion Guidance (Poster)
An Interpretability-augmented Genetic Expert for Deep Molecular Optimization (Poster)
Latent Space Refinement for Deep Generative Models (Poster)
Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration (Poster)
Self-Supervised Anomaly Detection via Neural Autoregressive Flows with Active Learning (Oral)
Accurate Imputation and Efficient Data Acquisitionwith Transformer-based VAEs (Oral)
Content-Based Image Retrieval from Weakly-Supervised Disentangled Representations (Oral)
Single Image Super-Resolution with Uncertainty Estimation for Lunar Satellite Images (Poster)
Latent Space Refinement for Deep Generative Models (Oral)
Conditional Generation of Periodic Signals with Fourier-Based Decoder (Poster)
Your Dataset is a Multiset and You Should Compress it Like One (Poster)
Probabilistic Hierarchical Forecasting with Deep Poisson Mixtures (Oral)
Sample-Efficient Generation of Novel Photo-acid Generator Molecules using a Deep Generative Model (Poster)
How to Reward Your Drug Agent? (Oral)
Entropic Issues in Likelihood-Based OOD Detection (Oral)
Certifiably Robust Variational Autoencoders (Poster)
Searching for the Weirdest Stars: A Convolutional Autoencoder-Based Pipeline For Detecting Anomalous Periodic Variable Stars (Poster)
Uncertainty-aware Labelled Augmentations for High Dimensional Latent Space Bayesian Optimization (Poster)
Transparent Liquid Segmentation for Robotic Pouring (Poster)
Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation (Poster)