Articles in the publication category
Neural Concept Formation in Knowledge Graphs
Exact and Efficient Adversarial Robustness with Decomposable Neural Networks
Is Parameter Learning via Weighted Model Integration Tractable?
An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games
Tractable Computation of Expected Kernels
JUICE: A Julia Package for Logic and Probabilistic Circuits
Conditional Sum-Product Networks: Modular Probabilistic Circuits via Gate Functions
Strudel: A fast and accurate learner of structured-decomposable probabilistic circuits
Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations
Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games
Handling Missing Data in Decision Trees: A Probabilistic Approach
Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing
Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures
Strudel: Learning Structured-Decomposable Probabilistic Circuits
From Variational to Deterministic Autoencoders
Hybrid Probabilistic Inference with Logical Constraints: Tractability and Message-Passing
On Tractable Computation of Expected Predictions
Automatic Bayesian density analysis
Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning
Visualizing and understanding Sum-Product Networks
Ensembles of density estimators for positive-unlabeled learning
Sum-product autoencoding: Encoding and decoding representations using sum-product networks
Mixed sum-product networks: A deep architecture for hybrid domains
Bayesian Nonparametric Hawkes Processes
Sum-Product Network structure learning by efficient product nodes discovery
Fast and Accurate Density Estimation with Extremely Randomized Cutset Networks
Encoding and Decoding Representations with Sum- and Max-Product Networks
End-to-end Learning of Deep Spatio-temporal Representations for Satellite Image Time Series Classification
Alternative Variable Splitting Methods to Learn Sum-Product Networks
Generative Probabilistic Models for Positive-Unlabeled Learning
Towards Representation Learning with Tractable Probabilistic Models
Multi-Label Classification with Cutset Networks
Learning Bayesian Random Cutset Forests
Learning Accurate Cutset Networks by Exploiting Decomposability
Simplifying, Regularizing and Strengthening Sum-Product Network Structure Learning
Handling Incomplete Heterogeneous Data using VAEs