A neuron-centric fusion method that clusters intermediate activations of independently trained models into importance-weighted centroids and fits the fused network to them, outperforming baselines in zero-shot non-IID settings.
Correlation-based pruning algorithm with weight compensation for feedforward neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Model Fusion via Retrofitting
A neuron-centric fusion method that clusters intermediate activations of independently trained models into importance-weighted centroids and fits the fused network to them, outperforming baselines in zero-shot non-IID settings.