Sparsity
Sparse Evolutionary Training
Introduced by Mocanu et al. in Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network ScienceDynamic Sparse Training method where weight mask is updated randomly periodically
Source: Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network SciencePapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Language Modelling | 16 | 2.89% |
| Diversity | 14 | 2.53% |
| Large Language Model | 10 | 1.81% |
| Object | 10 | 1.81% |
| Retrieval | 10 | 1.81% |
| In-Context Learning | 10 | 1.81% |
| Image Classification | 9 | 1.62% |
| Reinforcement Learning (RL) | 9 | 1.62% |
| Active Learning | 8 | 1.44% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
