# Equivariant-Aware Structured Pruning for Efficient Edge Deployment: A Comprehensive Framework with Adaptive Fine-Tuning

arXiv: https://arxiv.org/abs/2511.17242 · HTML: https://mlsanity.com/paper/2511.17242/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Builds on (most cited first, 13 of 13)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [General E(2)-Equivariant Steerable CNNs](https://mlsanity.com/paper/1911.08251/) (2019)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups](https://mlsanity.com/paper/2104.09459/) (2021)
- [RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration](https://mlsanity.com/paper/2411.06463/) (2024)
- [Efficient Structured Pruning and Architecture Searching for Group Convolution](https://mlsanity.com/paper/1811.09341/) (2018)

## Abstract (arXiv)

This paper presents a novel framework combining group equivariant convolutional neural networks (G-CNNs) with equivariant-aware structured pruning to produce compact, transformation-invariant models for resource-constrained environments. Equivariance to rotations is achieved through the C4 cyclic group via the e2cnn library,enabling consistent performance under geometric transformations while reducing computational overhead. Our approach introduces structured pruning that preserves equivariant properties by analyzing e2cnn layer structure and applying neuron-level pruning to fully connected components. To mitigate accuracy degradation, we implement adaptive fine-tuning that automatically triggers when accuracy drop exceeds 2%, using early stopping and learning rate scheduling for efficient recovery. The framework includes dynamic INT8 quantization and a comprehensive pipeline encompassing training, knowledge distillation, structured pruning, fine-tuning, and quantization. We evaluate our method on satellite imagery (EuroSAT) and standard benchmarks (CIFAR-10, Rotated MNIST) demonstrating effectiveness across diverse domains. Experimental results show 29.3% parameter reduction with significant accuracy recovery, demonstrating that structured pruning of equivariant networks achieves substantial compression while maintaining geometric robustness. Our pipeline provides a reproducible framework for optimizing equivariant models, bridging the gap between group-theoretic network design and practical deployment constraints, with particular relevance to satellite imagery analysis and geometric vision tasks.