A training strategy that grows GCN depth gradually, using LoRA fine-tuning and identity initialization, is claimed to reduce over-smoothing and improve accuracy of deep vanilla GCNs.
Advances in neural information processing systems29(2016)
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
-
Towards a deeper GCN: Alleviate over-smoothing with iterative training and fine-tuning
A training strategy that grows GCN depth gradually, using LoRA fine-tuning and identity initialization, is claimed to reduce over-smoothing and improve accuracy of deep vanilla GCNs.