3 citations · 10 across the 9 of their papers we have counts for
4 papers · 1 filter
Causal Cellular Context Transfer Learning (C3TL): An Efficient Architecture for Prediction of Unseen Perturbation Effects
Michael Scholkemper, Sach Mukherjee
Predicting the effects of chemical and genetic perturbations on quantitative cell states is a central challenge in computational biology, molecular medicine and drug discovery. Rec…
Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
Michael Scholkemper, Xinyi Wu, Ali Jadbabaie +1
Residual connections and normalization layers have become standard design choices for graph neural networks (GNNs), and were proposed as solutions to the mitigate the oversmoothing…
ICML 2023 Topological Deep Learning Challenge : Design and Results
Mathilde Papillon, Mustafa Hajij, Helen Jenne +53
This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning. The competi…
Learning the effective order of a hypergraph dynamical system
Leonie Neuhäuser, Michael Scholkemper, Francesco Tudisco +1
Dynamical systems on hypergraphs can display a rich set of behaviours not observable for systems with pairwise interactions. Given a distributed dynamical system with a putative hy…