Early-exit GNNs for link prediction move the speed-quality Pareto frontier on the HeaRT benchmark by allowing implicit early exiting without auxiliary losses.
Adaptive propagation graph con- volutional network.IEEE Transactions on Neural Networks and Learning Systems, 32(10): 4755–4760, October 2021
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
-
Early-Exit Graph Neural Networks for Link Prediction
Early-exit GNNs for link prediction move the speed-quality Pareto frontier on the HeaRT benchmark by allowing implicit early exiting without auxiliary losses.