output
20222024
most citedDropMessage: Unifying Random Dropping for Graph Neural Networks

64 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2022Show all

1 paper · 1 filter

cs.LG2022★ 64 cited

DropMessage: Unifying Random Dropping for Graph Neural Networks

Taoran Fang, Zhiqing Xiao, Chunping Wang +3

Graph Neural Networks (GNNs) are powerful tools for graph representation learning. Despite their rapid development, GNNs also face some challenges, such as over-fitting, over-smoot…