1 citations · 1 across the 1 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2019★ 1 cited
Explanatory Masks for Neural Network Interpretability
Lawrence Phillips, Garrett Goh, Nathan Hodas
Neural network interpretability is a vital component for applications across a wide variety of domains. In such cases it is often useful to analyze a network which has already been…
cs.LG2019
Sparse hierarchical representation learning on molecular graphs
Matthias Bal, Hagen Triendl, Mariana Assmann +6
Architectures for sparse hierarchical representation learning have recently been proposed for graph-structured data, but so far assume the absence of edge features in the graph. We…