InGSL reduces edge redundancy in existing graph structure learning methods by adding a mutual-information-guided diversity term, delivering better results with fewer edges across six tested frameworks.
Spectral net- works and locally connected networks on graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Informative Graph Structure Learning
InGSL reduces edge redundancy in existing graph structure learning methods by adding a mutual-information-guided diversity term, delivering better results with fewer edges across six tested frameworks.