Partial fusion interpolates between neural network ensembles and weight aggregation by only fusing the most similar neurons identified via partial optimal transport, enabling flexible cost-performance tradeoffs.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Sparsity allocation choices like ERK versus LAMP produce different post-repair accuracies for label-free recovery of pruned ResNets on image datasets, with a repair-sensitive transition regime at high sparsities.
citing papers explorer
-
Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
Partial fusion interpolates between neural network ensembles and weight aggregation by only fusing the most similar neurons identified via partial optimal transport, enabling flexible cost-performance tradeoffs.
-
How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability
Sparsity allocation choices like ERK versus LAMP produce different post-repair accuracies for label-free recovery of pruned ResNets on image datasets, with a repair-sensitive transition regime at high sparsities.