AAAI 2023 accepted papers on Probabilistic and scientific modeling

Molecules and proteins · 30 papers

• WSiP: Wave Superposition Inspired Pooling for Dynamic Interactions-Aware Trajectory Prediction (47 citations)
• LORE: Logical Location Regression Network for Table Structure Recognition (36 citations)
• DiffMD: A Geometric Diffusion Model for Molecular Dynamics Simulations (24 citations)
• Conditional Syntax Splitting for Non-monotonic Inference Operators (20 citations)
• Physics Guided Neural Networks for Time-Aware Fairness: An Application in Crop Yield Prediction (14 citations)
• Retrosynthesis Prediction with Local Template Retrieval (14 citations)
• Blending Advertising with Organic Content in E-commerce via Virtual Bids (10 citations)
• AlphaRoute: Large-Scale Coordinated Route Planning via Monte Carlo Tree Search (8 citations)
• Concurrent Multi-Label Prediction in Event Streams (8 citations)
• Learning Logical Reasoning Using an Intelligent Tutoring System: A Hybrid Approach to Student Modeling (7 citations)
• Reinforced Approximate Exploratory Data Analysis (7 citations)
• Grape Cold Hardiness Prediction via Multi-Task Learning (6 citations)

and 18 more in the interactive map.

Variational and generative sampling · 27 papers

• Spearman Rank Correlation Screening for Ultrahigh-Dimensional Censored Data (16 citations)
• A Tool for Generating Controllable Variations of Musical Themes Using Variational Autoencoders with Latent Space Regularisation (9 citations)
• Continuous Mixtures of Tractable Probabilistic Models (7 citations)
• Generative Label Enhancement with Gaussian Mixture and Partial Ranking (7 citations)
• Planning with Hidden Parameter Polynomial MDPs (7 citations)
• Latent Autoregressive Source Separation (6 citations)
• Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models (5 citations)
• Diffeomorphic Information Neural Estimation (5 citations)
• Accelerating Inverse Learning via Intelligent Localization with Exploratory Sampling (4 citations)
• A Latent-Variable Model for Intrinsic Probing (3 citations)
• Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping (3 citations)
• Local Intrinsic Dimensional Entropy (3 citations)

and 15 more in the interactive map.

Uncertainty and Gaussian processes · 21 papers

• The Unreasonable Effectiveness of Deep Evidential Regression (37 citations)
• BETA-CD: A Bayesian Meta-Learned Cognitive Diagnosis Framework for Personalized Learning (21 citations)
• Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty (21 citations)
• Kalman Bayesian Neural Networks for Closed-Form Online Learning (14 citations)
• Evidential Conditional Neural Processes (13 citations)
• Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap (11 citations)
• Scalable Bayesian Meta-Learning through Generalized Implicit Gradients (11 citations)
• AmnioML: Amniotic Fluid Segmentation and Volume Prediction with Uncertainty Quantification (7 citations)
• Better Peer Grading through Bayesian Inference (5 citations)
• Estimating Regression Predictive Distributions with Sample Networks (5 citations)
• Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling (5 citations)
• A Semi-parametric Model for Decision Making in High-Dimensional Sensory Discrimination Tasks (2 citations)

and 9 more in the interactive map.

Causal discovery · 16 papers

• Spatio-Temporal Neural Structural Causal Models for Bike Flow Prediction (32 citations)
• Causal Intervention for Human Trajectory Prediction with Cross Attention Mechanism (25 citations)
• Reinforcement Causal Structure Learning on Order Graph (15 citations)
• Improvement-Focused Causal Recourse (ICR) (13 citations)
• Causal Conditional Hidden Markov Model for Multimodal Traffic Prediction (10 citations)
• Evaluating Digital Agriculture Recommendations with Causal Inference (10 citations)
• Causal Effect Identification in Cluster DAGs (5 citations)
• Information-Theoretic Causal Discovery and Intervention Detection over Multiple Environments (5 citations)
• Vector Causal Inference between Two Groups of Variables (5 citations)
• A Simple Unified Approach to Testing High-Dimensional Conditional Independences for Categorical and Ordinal Data (3 citations)
• Multi-Level Wavelet Mapping Correlation for Statistical Dependence Measurement: Methodology and Performance (3 citations)
• Novel Ordering-Based Approaches for Causal Structure Learning in the Presence of Unobserved Variables (3 citations)

and 4 more in the interactive map.

Treatment effects · 11 papers

• Direct Heterogeneous Causal Learning for Resource Allocation Problems in Marketing (21 citations)
• Causal Inference with Conditional Instruments Using Deep Generative Models (18 citations)
• Estimating Geographic Spillover Effects of COVID-19 Policies from Large-Scale Mobility Networks (16 citations)
• Disentangled Representation for Causal Mediation Analysis (14 citations)
• Estimating Average Causal Effects from Patient Trajectories (13 citations)
• Weather2vec: Representation Learning for Causal Inference with Non-local Confounding in Air Pollution and Climate Studies (11 citations)
• Counterfactuals for the Future (6 citations)
• Learning Instrumental Variable from Data Fusion for Treatment Effect Estimation (4 citations)
• Identification and Estimation of the Probabilities of Potential Outcome Types Using Covariate Information in Studies with Non-compliance (1 citation)
• Identifying Selection Bias from Observational Data (1 citation)
• Probabilities of Potential Outcome Types in Experimental Studies: Identification and Estimation Based on Proxy Covariate Information (1 citation)

Dynamical systems · 11 papers

• EINNs: Epidemiologically-Informed Neural Networks (31 citations)
• Reachability Analysis of Neural Network Control Systems (11 citations)
• Neural Integro-Differential Equations (10 citations)
• Improving Robotic Tactile Localization Super-resolution via Spatiotemporal Continuity Learning and Overlapping Air Chambers (9 citations)
• Towards Safe AI: Sandboxing DNNs-Based Controllers in Stochastic Games (5 citations)
• Extracting Semantic-Dynamic Features for Long-Term Stable Brain Computer Interface (3 citations)
• Safety Verification of Nonlinear Systems with Bayesian Neural Network Controllers (3 citations)
• Combining Slow and Fast: Complementary Filtering for Dynamics Learning (2 citations)
• Compressed Decentralized Learning of Conditional Mean Embedding Operators in Reproducing Kernel Hilbert Spaces (2 citations)
• Counterfactual Dynamics Forecasting – a New Setting of Quantitative Reasoning (1 citation)
• Monitoring and Intervening on Large Populations of Weakly Coupled Processes with Social Impact Applications

Differential equations and PDEs · 9 papers

• Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations (21 citations)
• DMIS: Dynamic Mesh-Based Importance Sampling for Training Physics-Informed Neural Networks (18 citations)
• ODE-RSSM: Learning Stochastic Recurrent State Space Model from Irregularly Sampled Data (10 citations)
• PIXEL: Physics-Informed Cell Representations for Fast and Accurate PDE Solvers (9 citations)
• Lifting (D)QBF Preprocessing and Solving Techniques to (D)SSAT (3 citations)
• CasODE: Modeling Irregular Information Cascade via Neural Ordinary Differential Equations (Student Abstract) (1 citation)
• Deep Latent Regularity Network for Modeling Stochastic Partial Differential Equations (1 citation)
• Exploration on Physics-Informed Neural Networks on Partial Differential Equations (Student Abstract)
• Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs

Bayesian optimization · 4 papers

• Bayesian Optimization-Based Combinatorial Assignment (11 citations)
• High-Dimensional Dueling Optimization with Preference Embedding (3 citations)
• OPT-GAN: A Broad-Spectrum Global Optimizer for Black-Box Problems by Learning Distribution (2 citations)
• Mixed-Variable Black-Box Optimisation Using Value Proposal Trees