-
KDD 2021 Keynote Report
-
KDD 2021 Accepted Paper List with Links
-
Physics-informed neural networks with hard constraints for inverse design
-
Physics-guided Convolutional Neural Network (PhyCNN) for Data-driven Seismic Response Modeling
-
Multi-relational Poincaré Graph Embeddings
-
GANSpace: Discovering Interpretable GAN Controls
-
Towards physics-informed deep learning for turbulent flow prediction
-
WSDM 2021 Memo
-
Getting a CLUE: A Method for Explaining Uncertainty Estimates
-
Social Influence Does Matter: User Action Prediction for In-Feed Advertising
-
Neural Datalog Through Time: Informed Temporal Modeling via Logical Specification
-
Temporal Logic Point Processes
-
CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods
-
A general recurrent state space framework for modeling neural dynamics during decision-making
-
Non-reversible Gaussian processes for identifying latent dynamical structure in neural data
-
Implicit Neural Representations with Periodic Activation Functions
-
Deep Multimodal Fusion by Channel Exchanging
-
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
-
Teaching a GAN What Not to Learn
-
Multi-task Causal Learning with Gaussian Processes
-
Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network
-
Benchmarking Deep Learning Interpretability in Time Series Predictions
-
Interpretable Sequence Learning for COVID-19 Forecasting
-
Performative Prediction
-
Adapting Neural Networks for the Estimation of Treatment Effects
-
CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
-
Causal analysis of Covid-19 spread in Germany
-
Open Intent Extraction from Natural Language Interactions
-
On Learning Sets of Symmetric Elements
-
Community Interaction and Conflict on the Web
-
Semantic Search in Millions of Equations
-
Towards Automated Neural Interaction Discovering for Click-Through Rate Prediction
-
Kernel Assisted Learning for Personalized Dose Finding
-
Mining Persistent Activity in Continually Evolving Networks
-
Identifying Sepsis Subphenotypes via Time-Aware Multi-Modal Auto-Encoder
-
Heidegger: Interpretable Temporal Causal Discovery
-
A Framework for Recommending Accurate and Diverse Items Using Bayesian Graph Convolutional Neural Networks
-
Deep State-Space Generative Model For Correlated Time-to-Event Predictions
-
A Data Driven Graph Generative Model for Temporal Interaction Networks
-
Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
-
List-wise Fairness Criterion for Point Processes
-
A causal look at statistical definitions of discrimination