Timezone: »

Runtime Neural Pruning
Ji Lin · Yongming Rao · Jiwen Lu · Jie Zhou

Tue Dec 05 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #102

In this paper, we propose a Runtime Neural Pruning (RNP) framework which prunes the deep neural network dynamically at the runtime. Unlike existing neural pruning methods which produce a fixed pruned model for deployment, our method preserves the full ability of the original network and conducts pruning according to the input image and current feature maps adaptively. The pruning is performed in a bottom-up, layer-by-layer manner, which we model as a Markov decision process and use reinforcement learning for training. The agent judges the importance of each convolutional kernel and conducts channel-wise pruning conditioned on different samples, where the network is pruned more when the image is easier for the task. Since the ability of network is fully preserved, the balance point is easily adjustable according to the available resources. Our method can be applied to off-the-shelf network structures and reach a better tradeoff between speed and accuracy, especially with a large pruning rate.

Author Information

Ji Lin (Tsinghua University)
Yongming Rao (Tsinghua University)
Jiwen Lu (Tsinghua University)
Jie Zhou (Tsinghua University)

More from the Same Authors

  • 2021 Poster: DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification »
    Yongming Rao · Wenliang Zhao · Benlin Liu · Jiwen Lu · Jie Zhou · Cho-Jui Hsieh
  • 2021 Poster: Global Filter Networks for Image Classification »
    Yongming Rao · Wenliang Zhao · Zheng Zhu · Jiwen Lu · Jie Zhou
  • 2018 : Poster spotlight session. »
    Abdullah Salama · Wei-Cheng Chang · Aidan Gomez · Raphael Tang · FUXUN YU · Zhendong Zhang · Yuxin Zhang · Ji Lin · Stephen Tiedemann · Kun Bai · Sivaramakrishnan Sankarapandian · Marton Havasi · Jack Turner · Hsin-Pai Cheng · Yue Wang · Xiaofan Xu · Ruizhou Ding · Haoji Hu · Mohammad Shafiee · Christopher Blake · Chieh-Chi Kao · Daniel Kang · Yew Ken Chia · Amir Ashouri · Sourya Basu · Simon Wiedemann · Thorsten Laude