One-shot pruned graph and weight masks, when gradually denoised with gradient- and degree-based swapping, yield graph lottery tickets that are sparser and faster to find than iterative magnitude pruning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks
One-shot pruned graph and weight masks, when gradually denoised with gradient- and degree-based swapping, yield graph lottery tickets that are sparser and faster to find than iterative magnitude pruning.