A dynamic sparse training method that restricts weights to a learnable set of diagonals, preserving sparsity in both forward and backward passes to obtain GPU speedups at accuracy close to unstructured sparsity.
On improving deep learning generalization with adaptive sparse connectivity
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse neural networks with adaptive sparse connectivity, which by design have a strict parameter budget during the training phase, have better generalization capabilities than their fully-connected counterparts. Besides this, we propose a new technique to train these sparse models by combining the Sparse Evolutionary Training (SET) procedure with neurons pruning. Operated on MultiLayer Perceptron (MLP) and tested on 15 datasets, our proposed technique zeros out around 50% of the hidden neurons during training, while having a linear number of parameters to optimize with respect to the number of neurons. The results show a competitive classification and generalization performance.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dynamic Sparse Training of Diagonally Sparse Networks
A dynamic sparse training method that restricts weights to a learnable set of diagonals, preserving sparsity in both forward and backward passes to obtain GPU speedups at accuracy close to unstructured sparsity.