EDEN uses structural entropy to build a hierarchical knowledge tree over digraphs and distills parent-to-child knowledge to boost graph-neural-network accuracy, though the mutual-information lower bound it relies on is invalid.
We default to using AUC and AP in the evaluation of the link prediction tasks, and ACC to evaluate the predictive performance of node-level tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Toward Data-centric Directed Graph Learning: An Entropy-driven Approach
EDEN uses structural entropy to build a hierarchical knowledge tree over digraphs and distills parent-to-child knowledge to boost graph-neural-network accuracy, though the mutual-information lower bound it relies on is invalid.