2 papers
cs.LG2024
RepAct: The Re-parameterizable Adaptive Activation Function
Xian Wu, Qingchuan Tao, Shuang Wang
Addressing the imperative need for efficient artificial intelligence in IoT and edge computing, this study presents RepAct, a re-parameterizable adaptive activation function tailor…
cs.LG2023★ 12 cited
Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation
Shuang Wang, Bahaeddin Eravci, Rustam Guliyev +1
Graph Neural Network (GNN) training and inference involve significant challenges of scalability with respect to both model sizes and number of layers, resulting in degradation of e…