Lossy and Lossless (L$^2$) Post-training Model Size Compression

1 code implementation • 8 Aug 2023 • Yumeng Shi, Shihao Bai, Xiuying Wei, Ruihao Gong, Jianlei Yang

Then, a dedicated differentiable counter is introduced to guide the optimization of lossy compression to arrive at a more suitable point for later lossless compression.

Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms

no code implementations • 20 Mar 2023 • Ao Zhou, Jianlei Yang, Yingjie Qi, Yumeng Shi, Tong Qiao, Weisheng Zhao, Chunming Hu

Moreover, HGNAS achieves hardware awareness during the GNN architecture design by leveraging a hardware performance predictor, which could balance the GNN model accuracy and efficiency corresponding to the characteristics of targeted devices.

Edge-computing Neural Architecture Search

Lossy and Lossless (L2) Post-training Model Size Compression

1 code implementation • ICCV 2023 • Yumeng Shi, Shihao Bai, Xiuying Wei, Ruihao Gong, Jianlei Yang

Then, a dedicated differentiable counter is introduced to guide the optimization of lossy compression to arrive at a more suitable point for later lossless compression.