64 citations · 362 across the 43 of their papers we have counts for
4 papers · 1 filter
Measuring Learned Equivariance: An Information Theoretic Approach
Claire Schlesinger, Wolfgang Gatterbauer, Robin Walters
Learning symmetries through data augmentation offers an alternative to architectural equivariance, but does not guarantee that a network respects those symmetries. Measuring learne…
Towards Unbiased Exploration in Partial Label Learning
Zsolt Zombori, Agapi Rissaki, Kristóf Szabó +2
We consider learning a probabilistic classifier from partially-labelled supervision (inputs denoted with multiple possibilities) using standard neural architectures with a softmax…
Factorized Graph Representations for Semi-Supervised Learning from Sparse Data
Krishna Kumar P., Paul Langton, Wolfgang Gatterbauer
The paper introduces a scalable method that estimates class compatibility matrices directly from extremely sparsely labeled graphs using factorized graph representations, enabling…
Semi-Supervised Learning with Heterophily
Wolfgang Gatterbauer
We derive a family of linear inference algorithms that generalize existing graph-based label propagation algorithms by allowing them to propagate generalized assumptions about "att…