Directed Networks
Towards Hardware-AwareTractable LearningofProbabilisticModels
Smart portable applications increasingly rely on edge computing due to privacy andlatencyconcerns.
Constraint-based Causal Structure Learning with Consistent Separating Sets
This paper concerns, more specifically, the inconsistency of separating sets used to remove dispensable edges, iteratively, based on conditional independence tests.
On Learning Markov Chains
Yi Hao, Alon Orlitsky, Venkatadheeraj Pichapati
Neural Information Processing Systems http://nips.cc/
D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
Muhan Zhang, Shali Jiang, Zhicheng Cui, Roman Garnett, Yixin Chen
Graph structured data are abundant in the real world.
Amortized Bethe Free Energy Minimization for Learning MRFs
Neural Information Processing Systems http://nips.cc/
Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?
Notably, most real-world homophilic and heterophilic graphs are comprised of a mixture of nodes in both homophilic and heterophilic structural patterns, exhibiting a structural disparity.