Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework.
Junxiang WangHongyi LiZheng ChaiYongchao WangYue ChengLiang ZhaoPublished in: CoRR (2021)
Keyphrases
- probabilistic model
- formal model
- mathematical model
- computational model
- conceptual model
- theoretical framework
- dependency graph
- graph model
- conceptual framework
- unified model
- random walk
- support vector machine
- network structure
- probability distribution
- convex optimization
- prior knowledge
- high level
- graphical representation
- neural network