Neural networks (NNs) are equipped with increasingly many parameters and require more and more resource for deployment. Researchers have explored various ways to improve the efficiency of NNs by identifying and reducing the redundancy, such as pruning or quantizing unimportant weights. Symmetry in the NN architectures has been identified by prior work as a possible type of redundancy, but exploiting it for efficient inference is not yet explored. In this work, we formalize the symmetry of parameters and intermediate values in NNs using the statistical property of exchangeablility. We identify that exchangeable values in NN computation may contain overlapping information, leading to redundancy. Exploiting the insight, we derive a principled general dynamic pruning algorithm ExPrune to remove symmetry-induced redundancy on a per-input basis. We also provide an instantiation of ExPrune that performs neuron-level dynamic pruning by predicting negative inputs to ReLU activations. We evaluate ExPrune on two computer vision models, one graph model and one language model. ExPrune provides 10.98--26.3% reduction in FLOPs with negligible accuracy drop and 21.01--39.05% reduction in FLOPs with at most 1% accuracy drop. We also demonstrate that ExPrune composes with static pruning. On models that have been aggressively pruned statically, ExPrune provides additional 10.24--11.11% reduction in FLOPs with negligible accuracy drop and 13.91--14.39% reduction in FLOPs with at most 1% accuracy drop.
View on arXiv@article{chen2025_2506.02210,
title={ Exchangeability in Neural Network Architectures and its Application to Dynamic Pruning },
author={ Tianlang Chen and Yifan Yang and Sara Achour },
journal={arXiv preprint arXiv:2506.02210},
year={ 2025 }
}