ICLR 22 submitted paper list

ICLR 22 submitted papers list

Time series

• PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series

• Context-invariant, multi-variate time series representations

• TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation

• Multivariate Time Series Forecasting with Latent Graph Inference

• Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy

• TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting

• IIT-GAN: Irregular and Intermittent Time-series Synthesis with Generative Adversarial Networks

• Graph-Guided Network for Irregularly Sampled Multivariate Time Series

• Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

• DeepFIB: Self-Imputation for Time Series Anomaly Detection

• Spatiotemporal Representation Learning on Time Series with Dynamic Graph ODEs

• Non-Denoising Forward-Time Diffusions

EBM

• Diffusion-Based Representation Learning

• Autoregressive Diffusion Models

• Unconditional Diffusion Guidance

• PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior

• Progressive Distillation for Fast Sampling of Diffusion Models

• Score-Based Generative Modeling with Critically-Damped Langevin Diffusion

• BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

• ST-DDPM: Explore Class Clustering for Conditional Diffusion Probabilistic Models

• Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models

• Denoising Diffusion Gamma Models

• Maximum Likelihood Training of Parametrized Diffusion Model

• Gotta Go Fast When Generating Data with Score-Based Models

• Learning to Efficiently Sample from Diffusion Probabilistic Models

• SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

• High Precision Score-based Diffusion Models

• Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory

• YOUR AUTOREGRESSIVE GENERATIVE MODEL CAN BE BETTER IF YOU TREAT IT AS AN ENERGY-BASED ONE

Dynamic systems

• Composing Partial Differential Equations with Physics-Aware Neural Networks

• Denoising Likelihood Score Matching for Conditional Score-based Data Generation

• Learning Efficient and Robust Ordinary Differential Equations via Diffeomorphisms

• LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations

• Physics-Informed Neural Operator for Learning Partial Differential Equations

• A framework of deep neural networks via the solution operator of partial differential equations

• NODEAttack: Adversarial Attack on the Energy Consumption of Neural ODEs

• D-CODE: Discovering Closed-form ODEs from Observed Trajectories

• PNODE: A memory-efficient neural ODE framework based on high-level adjoint differentiation

• SketchODE: Learning neural sketch representation in continuous time

GNN

• GRAND++: Graph Neural Diffusion with A Source Term

• Space-Time Graph Neural Networks