mlsanityData to 14 Oct 2026

Structured Pruning for Efficient ConvNets via Incremental Regularization

arXiv 1811.08390 ↗First posted 20 Nov 2018cs.CV cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factors, which neglects the fact that the expressiveness of CNNs is fragile and needs a more gentle way of regularization for the networks to adapt during pruning. To solve this problem, we propose a new regularization-based pruning method (named IncReg) to incrementally assign different regularization factors to different weight groups based on their relative importance, whose effectiveness is proved on popular CNNs compared with state-of-the-art methods.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 1; 2023: 3; 2024: 4; 2025: 2.

15 papers.

Sort:

By area:

  1. 2021Accelerating Sparse Deep Neural Networkscited by 223
  2. 2024ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Modelscited by 45
  3. 2021Recent Advances on Neural Network Pruning at Initializationcited by 41
  4. 2022Dual Lottery Ticket Hypothesiscited by 27
  5. 2023Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruningcited by 16
  6. 2021Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNNcited by 9
  7. 2024Is Oracle Pruning the True Oracle?cited by 7
  8. 2024Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neuronscited by 6
  9. 2023Dynamic Structure Pruning for Compressing CNNscited by 5
  10. 2021Alternate Model Growth and Pruning for Efficient Training of Recommendation Systemscited by 3
  11. 2021Dynamical Isometry: The Missing Ingredient for Neural Network Pruningcited by 2
  12. 2024Enhanced Sparsification via Stimulative Trainingcited by 2
3 more
  1. 2025One-Cycle Structured Pruning via Stability-Driven Subnetwork Searchcited by 1
  2. 2023Neural Language Model Pruning for Automatic Speech Recognitioncited by 0
  3. 2025Catalyst: a Novel Regularizer for Structured Pruning with Auxiliary Extension of Parameter Spacecited by 0