`

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





Workshop Home Page

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