Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,786 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Oct 201919922001200920172026
1 result for “Connectivity-Aware”
DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decompositioncs.LG

DeGNN improves graph neural networks by decomposing graphs.

problem Graph Convolutional Networks (GCNs) suffer from oversmoothing and limited depth.
method Characterized oversmoothing through information theory, proposed DeGNN for automatic graph decomposition.
result DeGNN boosts performance of general GNNs and achieves state-of-the-art results.
Graph Neural NetworksGraph Convolutional NetworksOversmoothingGraph DecompositionConnectivity-Aware
2019-10-10abs ↗pdf ↗