CUP: Cluster Pruning for Compressing Deep Neural Networks

Rahul Duggal, Cao Xiao, Richard Vuduc, Duen Horng Chau, Jimeng Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We propose CUP, a new method for compressing and accelerating deep neural networks. At its core, CUP achieves compression by clustering and pruning similar filters in each layer. For clustering, CUP uses hierarchical clustering which allows for an elegant parameterization of model capacity through a single hyper-parameter t. We observe that by increasing t, CUP can dynamically reduce model capacity through non-uniform layer-wise pruning leading to two advantages. First, CUP can effectively compress a model to within the desired compute budget through a simple line-search on t. Second, through a simple extension, CUP can obtain the pruned model in a single training pass leading to large savings in training time. On Imagenet, CUP leads to a 2.47× FLOPS reduction on Resnet-50 with less than 1% drop in top-5 accuracy. Notably, in the retrain-free setting, CUP-RF saves over 10 hours of training time on 3 GPUs, in comparison to state-of-the-art methods. The code for CUP is open sourced.

Original languageEnglish (US)
Title of host publicationProceedings - 2021 IEEE International Conference on Big Data, Big Data 2021
EditorsYixin Chen, Heiko Ludwig, Yicheng Tu, Usama Fayyad, Xingquan Zhu, Xiaohua Tony Hu, Suren Byna, Xiong Liu, Jianping Zhang, Shirui Pan, Vagelis Papalexakis, Jianwu Wang, Alfredo Cuzzocrea, Carlos Ordonez
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages5
ISBN (Electronic)9781665439022
StatePublished - 2021
Event2021 IEEE International Conference on Big Data, Big Data 2021 - Virtual, Online, United States
Duration: Dec 15 2021Dec 18 2021

Publication series

NameProceedings - 2021 IEEE International Conference on Big Data, Big Data 2021


Conference2021 IEEE International Conference on Big Data, Big Data 2021
Country/TerritoryUnited States
CityVirtual, Online


  • Compact
  • Efficient
  • Neural Net
  • Pruning

ASJC Scopus subject areas

  • Information Systems and Management
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Information Systems


Dive into the research topics of 'CUP: Cluster Pruning for Compressing Deep Neural Networks'. Together they form a unique fingerprint.

Cite this