ICML 22 accepted paper list

ICML 22 accepted papers list

Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance
Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models
Latent Diffusion Energy-Based Model for Interpretable Text Modelling
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
Equivariant Diffusion for Molecule Generation in 3D
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Diffusion Models for Adversarial Purification
Planning with Diffusion for Flexible Behavior Synthesis
Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score Matching
Diffusion bridges vector quantized variational autoencoders
Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations
Score-Guided Intermediate Level Optimization: Fast Langevin Mixing for Inverse Problems
Score matching enables causal discovery of nonlinear additive noise models

Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection
Learning of Cluster-based Feature Importance for Electronic Health Record Time-series
Modeling Irregular Time Series with Continuous Recurrent Units
Domain Adaptation for Time Series Forecasting via Attention Sharing
Utilizing Expert Features for Contrastive Learning of Time-Series Representations
Reconstructing nonlinear dynamical systems from multi-modal time series
Adaptive Conformal Predictions for Time Series
TACTiS: Transformer-Attentional Copulas for Time Series
Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion
DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting

Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations
Composing Partial Differential Equations with Physics-Aware Neural Networks
On Numerical Integration in Neural Ordinary Differential Equations
Neural Laplace: Learning diverse classes of differential equations in the Laplace domain
Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks
Learning to Solve PDE-constrained Inverse Problems with Graph Networks

Conditional GANs with Auxiliary Discriminative Classifier
Exploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling
Structure-preserving GANs
A Neural Tangent Kernel Perspective of GANs

SkexGen: Generating CAD Construction Sequences by Autoregressive VAE with Disentangled Codebooks
Mitigating modality collapse in multimodal VAEs via impartial optimization
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization
Bit Prioritization in Variational Autoencoders via Progressive Coding
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
Accelerating Bayesian Optimization for Protein Design with Denoising Autoencoders
Diffusion bridges vector quantized variational autoencoders

Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
Local Augmentation for Graph Neural Networks
G-Mixup: Graph Data Augmentation for Graph Classification
p-Laplacian Based Graph Neural Networks
NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning
Rethinking Graph Neural Networks for Anomaly Detection
A New Perspective on the Effects of Spectrum in Graph Neural Networks
G22CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters
Convergence of Invariant Graph Networks
Graph-Coupled Oscillator Networks
Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling
Cross-Space Active Learning on Graph Convolutional Networks