AAAI 2024 accepted papers on Probabilistic and scientific modeling

Molecules and proteins · 55 papers

• BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Driving (64 citations)
• Prot2Text: Multimodal Protein’s Function Generation with GNNs and Transformers (41 citations)
• FlightBERT++: A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework (32 citations)
• A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generation (21 citations)
• Text-Guided Molecule Generation with Diffusion Language Model (20 citations)
• Social Physics Informed Diffusion Model for Crowd Simulation (16 citations)
• Adversarial Socialbots Modeling Based on Structural Information Principles (15 citations)
• From GARCH to Neural Network for Volatility Forecast (13 citations)
• PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction (13 citations)
• Symbolic Cognitive Diagnosis via Hybrid Optimization for Intelligent Education Systems (13 citations)
• GxVAEs: Two Joint VAEs Generate Hit Molecules from Gene Expression Profiles (12 citations)
• Binding-Adaptive Diffusion Models for Structure-Based Drug Design (11 citations)

and 43 more in the interactive map.

Causal discovery · 21 papers

• CUTS+: High-Dimensional Causal Discovery from Irregular Time-Series (37 citations)
• Root Cause Analysis in Microservice Using Neural Granger Causal Discovery (33 citations)
• Identification of Causal Structure in the Presence of Missing Data with Additive Noise Model (8 citations)
• Towards the Disappearing Truth: Fine-Grained Joint Causal Influences Learning with Hidden Variable-Driven Causal Hypergraphs in Time Series (8 citations)
• Causal Representation Learning via Counterfactual Intervention (7 citations)
• Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction (6 citations)
• TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences (6 citations)
• Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants (5 citations)
• Mastering Context-to-Label Representation Transformation for Event Causality Identification with Diffusion Models (5 citations)
• Multi-Granularity Causal Structure Learning (5 citations)
• Causal Discovery from Poisson Branching Structural Causal Model Using High-Order Cumulant with Path Analysis (3 citations)
• Effective Causal Discovery under Identifiable Heteroscedastic Noise Model (3 citations)

and 9 more in the interactive map.

Variational and generative sampling · 18 papers

• Distribution-Conditioned Adversarial Variational Autoencoder for Valid Instrumental Variable Generation (7 citations)
• LINGO-Space: Language-Conditioned Incremental Grounding for Space (7 citations)
• Using Stratified Sampling to Improve LIME Image Explanations (7 citations)
• MorphVAE: Advancing Morphological Design of Voxel-Based Soft Robots with Variational Autoencoders (6 citations)
• GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework (5 citations)
• Colour Passing Revisited: Lifted Model Construction with Commutative Factors (4 citations)
• Direct Amortized Likelihood Ratio Estimation (4 citations)
• Effectiveness of Constant Stepsize in Markovian LSA and Statistical Inference (3 citations)
• QCS-SGM+: Improved Quantized Compressed Sensing with Score-Based Generative Models (3 citations)
• Robustly Train Normalizing Flows via KL Divergence Regularization (3 citations)
• Understanding Likelihood of Normalizing Flow and Image Complexity through the Lens of Out-of-Distribution Detection (3 citations)
• Neural Network Approximators for Marginal MAP in Probabilistic Circuits (2 citations)

and 6 more in the interactive map.

Uncertainty and Gaussian processes · 17 papers

• Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction (23 citations)
• Deep Active Learning with Noise Stability (22 citations)
• Gaussian Process Neural Additive Models (11 citations)
• One Step Closer to Unbiased Aleatoric Uncertainty Estimation (8 citations)
• Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression (7 citations)
• Learning Diffusions under Uncertainty (6 citations)
• Full Bayesian Significance Testing for Neural Networks (5 citations)
• Sparse Variational Student-t Processes (5 citations)
• Efficient Nonparametric Tensor Decomposition for Binary and Count Data (4 citations)
• Bayesian Inference with Complex Knowledge Graph Evidence (3 citations)
• Learning Bayesian Network Classifiers to Minimize the Class Variable Parameters (3 citations)
• Uncertainty Quantification for Data-Driven Change-Point Learning via Cross-Validation (3 citations)

and 5 more in the interactive map.

Dynamical systems · 15 papers

• Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model (47 citations)
• A Local-Ascending-Global Learning Strategy for Brain-Computer Interface (20 citations)
• Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification (12 citations)
• MA-Net: Rethinking Neural Unit in the Light of Astrocytes (7 citations)
• Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems (4 citations)
• Neural Time-Reversed Generalized Riccati Equation (3 citations)
• Nowcasting Temporal Trends Using Indirect Surveys (3 citations)
• Automated State Estimation for Summarizing the Dynamics of Complex Urban Systems Using Representation Learning (2 citations)
• Dynamic Tangled Derivative Logic of Metric Spaces (2 citations)
• Exact Inference for Continuous-Time Gaussian Process Dynamics (2 citations)
• Learning Hybrid Dynamics Models with Simulator-Informed Latent States (2 citations)
• Learning Reduced Fluid Dynamics (1 citation)

and 3 more in the interactive map.

Treatment effects · 12 papers

• Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment (11 citations)
• Instrumental Variable Estimation for Causal Inference in Longitudinal Data with Time-Dependent Latent Confounders (10 citations)
• Contrastive Balancing Representation Learning for Heterogeneous Dose-Response Curves Estimation (8 citations)
• Probabilities of Causation with Nonbinary Treatment and Effect (6 citations)
• Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing (3 citations)
• Exploiting Geometry for Treatment Effect Estimation via Optimal Transport (3 citations)
• Adversarially Balanced Representation for Continuous Treatment Effect Estimation (2 citations)
• KG-TREAT: Pre-training for Treatment Effect Estimation by Synergizing Patient Data with Knowledge Graphs (2 citations)
• NESTER: An Adaptive Neurosymbolic Method for Causal Effect Estimation (2 citations)
• Uncertainty Quantification in Heterogeneous Treatment Effect Estimation with Gaussian-Process-Based Partially Linear Model (2 citations)
• Discovering Heterogeneous Causal Effects in Relational Data (1 citation)
• The Causal Impact of Credit Lines on Spending Distributions (1 citation)

Differential equations and PDEs · 11 papers

• Neural Oscillators for Generalization of Physics-Informed Machine Learning (19 citations)
• Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics (14 citations)
• An Interpretable Approach to the Solutions of High-Dimensional Partial Differential Equations (10 citations)
• Neural Physical Simulation with Multi-Resolution Hash Grid Encoding (5 citations)
• PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion (4 citations)
• Physics-Informed Representation and Learning: Control and Risk Quantification (4 citations)
• SHoP: A Deep Learning Framework for Solving High-Order Partial Differential Equations (4 citations)
• Component Fourier Neural Operator for Singularly Perturbed Differential Equations (3 citations)
• Operator-Learning-Inspired Modeling of Neural Ordinary Differential Equations (3 citations)
• Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution (3 citations)
• SNN-PDE: Learning Dynamic PDEs from Data with Simplicial Neural Networks (2 citations)

Bayesian optimization · 11 papers

• Constrained Bayesian Optimization under Partial Observations: Balanced Improvements and Provable Convergence (15 citations)
• Are You Concerned about Limited Function Evaluations: Data-Augmented Pareto Set Learning for Expensive Multi-Objective Optimization (11 citations)
• Pareto Front-Diverse Batch Multi-Objective Bayesian Optimization (9 citations)
• Multi-Objective Bayesian Optimization with Active Preference Learning (8 citations)
• PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance (7 citations)
• Learning Encodings for Constructive Neural Combinatorial Optimization Needs to Regret (6 citations)
• Grey-Box Bayesian Optimization for Sensor Placement in Assisted Living Environments (3 citations)
• Stochastic Bayesian Optimization with Unknown Continuous Context Distribution via Kernel Density Estimation (2 citations)
• Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization (1 citation)
• Kernelized Normalizing Constant Estimation: Bridging Bayesian Quadrature and Bayesian Optimization
• Preference-Aware Constrained Multi-Objective Bayesian Optimization (Student Abstract)