Dissecting Supervised Contrastive Learning

1 code implementation • 17 Feb 2021 • Florian Graf, Christoph D. Hofer, Marc Niethammer, Roland Kwitt

Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks.

Contrastive Learning

Topologically Densified Distributions

1 code implementation • ICML 2020 • Christoph D. Hofer, Florian Graf, Marc Niethammer, Roland Kwitt

We study regularization in the context of small sample-size learning with over-parameterized neural networks.

Graph Filtration Learning

1 code implementation • ICML 2020 • Christoph D. Hofer, Florian Graf, Bastian Rieck, Marc Niethammer, Roland Kwitt

We propose an approach to learning with graph-structured data in the problem domain of graph classification.

General Classification Graph Classification