# Designing Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition

arXiv: https://arxiv.org/abs/2412.11813 · HTML: https://mlsanity.com/paper/2412.11813/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 97 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 30 of 32)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations](https://mlsanity.com/paper/1704.02463/) (2017)
- [Understanding Attention and Generalization in Graph Neural Networks](https://mlsanity.com/paper/1905.02850/) (2019)
- [A Riemannian Network for SPD Matrix Learning](https://mlsanity.com/paper/1608.04233/) (2016)
- [Adaptive Graph Convolutional Neural Networks](https://mlsanity.com/paper/1801.03226/) (2018)
- [Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition](https://mlsanity.com/paper/1607.07043/) (2016)
- [An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1611.06067/) (2016)
- [View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1703.08274/) (2017)
- [MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks](https://mlsanity.com/paper/1711.06798/) (2017)
- [Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks](https://mlsanity.com/paper/1603.07772/) (2016)
- [Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks](https://mlsanity.com/paper/1707.05740/) (2017)
- [Building Deep Networks on Grassmann Manifolds](https://mlsanity.com/paper/1611.05742/) (2016)
- [RGB-D-based Human Motion Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/1711.08362/) (2017)
- [Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization](https://mlsanity.com/paper/2206.01198/) (2022)
- [Structured Pruning of Neural Networks with Budget-Aware Regularization](https://mlsanity.com/paper/1811.09332/) (2018)
- [A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding](https://mlsanity.com/paper/1807.00676/) (2018)
- [Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2112.03328/) (2021)
- [Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection](https://mlsanity.com/paper/1607.02737/) (2016)
- [Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition](https://mlsanity.com/paper/1802.09834/) (2018)
- [DeepGRU: Deep Gesture Recognition Utility](https://mlsanity.com/paper/1810.12514/) (2018)

## Abstract (arXiv)

Deep neural networks (DNNs) are nowadays witnessing a major success in solving many pattern recognition tasks including skeleton-based classification. The deployment of DNNs on edge-devices, endowed with limited time and memory resources, requires designing lightweight and efficient variants of these networks. Pruning is one of the lightweight network design techniques that operate by removing unnecessary network parts, in a structured or an unstructured manner, including individual weights, neurons or even entire channels. Nonetheless, structured and unstructured pruning methods, when applied separately, may either be inefficient or ineffective. In this paper, we devise a novel semi-structured method that discards the downsides of structured and unstructured pruning while gathering their upsides to some extent. The proposed solution is based on a differentiable cascaded parametrization which combines (i) a band-stop mechanism that prunes weights depending on their magnitudes, (ii) a weight-sharing parametrization that prunes connections either individually or group-wise, and (iii) a gating mechanism which arbitrates between different group-wise and entry-wise pruning. All these cascaded parametrizations are built upon a common latent tensor which is trained end-to-end by minimizing a classification loss and a surrogate tensor rank regularizer. Extensive experiments, conducted on the challenging tasks of action and hand-gesture recognition, show the clear advantage of our proposed semi-structured pruning approach against both structured and unstructured pruning, when taken separately, as well as the related work.