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.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Dec 201919922001200920172026
1 result for “sink-to-source”
Tracing the Propagation Path: A Flow Perspective of Representation Learning on Graphscs.LG

FlowGN tackles graph representation learning by tracing information flow paths.

problem GCNs struggle with over-smoothing and scalability issues.
method FlowGN introduces a 'Sourceo oSink' mode and 'information flow path' concept.
result FlowGN outperforms state-of-the-art GCNs in public datasets.
graph convolutional networksrepresentation learninginformation flowsink-to-sourcesource-to-sink
2019-12-12abs ↗pdf ↗