AAAI 2022 accepted papers on Probabilistic and scientific modeling
75 of the 1,319 papers accepted at AAAI 2022 (5.7%) are on Probabilistic and scientific modeling, compared with 7.2% at AAAI 2021. They fall into 8 topics.
See AAAI 2022 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Molecules and proteins · 19 papers
- STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction (106 citations)
- Social Interpretable Tree for Pedestrian Trajectory Prediction (62 citations)
- Qubit Routing Using Graph Neural Network Aided Monte Carlo Tree Search (24 citations)
- Amortized Generation of Sequential Algorithmic Recourses for Black-Box Models (20 citations)
- A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations (15 citations)
- Bridging LTLf Inference to GNN Inference for Learning LTLf Formulae (14 citations)
- Online Missing Value Imputation and Change Point Detection with the Gaussian Copula (13 citations)
- Latent Space Explanation by Intervention (11 citations)
- SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal Patterns with an Autoregressive Embedding Loss (11 citations)
- ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems (10 citations)
- Fast and More Powerful Selective Inference for Sparse High-Order Interaction Model (8 citations)
- Span-Based Semantic Role Labeling with Argument Pruning and Second-Order Inference (7 citations)
and 7 more in the interactive map.
Causal discovery · 17 papers
- Debiasing NLU Models via Causal Intervention and Counterfactual Reasoning (35 citations)
- Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition (30 citations)
- Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction (23 citations)
- Learning Human Driving Behaviors with Sequential Causal Imitation Learning (21 citations)
- On Causally Disentangled Representations (16 citations)
- A Hybrid Causal Structure Learning Algorithm for Mixed-Type Data (14 citations)
- Training a Resilient Q-network against Observational Interference (14 citations)
- Residual Similarity Based Conditional Independence Test and Its Application in Causal Discovery (12 citations)
- VACA: Designing Variational Graph Autoencoders for Causal Queries (11 citations)
- Reasoning about Causal Models with Infinitely Many Variables (10 citations)
- Unsupervised Editing for Counterfactual Stories (10 citations)
- Unit Selection with Causal Diagram (8 citations)
and 5 more in the interactive map.
Variational and generative sampling · 14 papers
- FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-Sectional Stock Returns (73 citations)
- Fully Spiking Variational Autoencoder (44 citations)
- MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning (42 citations)
- DeepStochLog: Neural Stochastic Logic Programming (37 citations)
- Unsupervised Anomaly Detection by Robust Density Estimation (27 citations)
- Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise (26 citations)
- Deconvolutional Density Network: Modeling Free-Form Conditional Distributions (10 citations)
- A Computable Definition of the Spectral Bias (6 citations)
- Entropy Estimation via Normalizing Flow (5 citations)
- RID-Noise: Towards Robust Inverse Design under Noisy Environments (5 citations)
- Competing Mutual Information Constraints with Stochastic Competition-Based Activations for Learning Diversified Representations (4 citations)
- Knowledge Distillation via Constrained Variational Inference (4 citations)
and 2 more in the interactive map.
Uncertainty and Gaussian processes · 6 papers
- Improving Evidential Deep Learning via Multi-Task Learning (28 citations)
- Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate (24 citations)
- Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates (16 citations)
- Detecting Misclassification Errors in Neural Networks with a Gaussian Process Model (9 citations)
- Inference and Learning with Model Uncertainty in Probabilistic Logic Programs (3 citations)
- Characterization of Incentive Compatibility of an Ex-ante Constrained Player (2 citations)
Dynamical systems · 6 papers
- Conditional Local Convolution for Spatio-Temporal Meteorological Forecasting (92 citations)
- Verification of Neural-Network Control Systems by Integrating Taylor Models and Zonotopes (33 citations)
- Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems (25 citations)
- Planning with Biological Neurons and Synapses (4 citations)
- Hyperverlet: A Symplectic Hypersolver for Hamiltonian Systems (2 citations)
- Leaping through Time with Gradient-Based Adaptation for Recommendation (1 citation)
Differential equations and PDEs · 6 papers
- Spline-PINN: Approaching PDEs without Data Using Fast, Physics-Informed Hermite-Spline CNNs (60 citations)
- Solving PDE-Constrained Control Problems Using Operator Learning (16 citations)
- Latent Time Neural Ordinary Differential Equations (11 citations)
- Shaping Noise for Robust Attributions in Neural Stochastic Differential Equations (11 citations)
- Neural Piecewise-Constant Delay Differential Equations (8 citations)
- HoD-Net: High-Order Differentiable Deep Neural Networks and Applications (5 citations)
