Shaoyi Huang

model compression (2) knowledge distillation (1) neural network optimization (1) efficient computing (1) model pruning (1) language model (1) attention head (1) overfitting reduction (1) homomorphic encryption (1) graph convolutional network (1) polynomial approximation (1) transformer-based language model (1) encrypted inference (1) private inference (1) head pruning (1) peer distillation (1) progressive knowledge distillation (1) pretrain-and-finetune paradigm (1) privacy-preserving machine learning (1) multiplication depth (1)