# Fast Sparse ConvNets

arXiv: https://arxiv.org/abs/1911.09723 · HTML: https://mlsanity.com/paper/1911.09723/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2019.

## Built on by (most cited first, 30 of 86)

- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [Accelerating Sparse Deep Neural Networks](https://mlsanity.com/paper/2104.08378/) (2021)
- [MegaBlocks: Efficient Sparse Training with Mixture-of-Experts](https://mlsanity.com/paper/2211.15841/) (2022)
- [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021)
- [Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better](https://mlsanity.com/paper/2106.08962/) (2021)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks](https://mlsanity.com/paper/2102.08124/) (2021)
- [AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks](https://mlsanity.com/paper/2106.12379/) (2021)
- [Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better](https://mlsanity.com/paper/2112.09824/) (2021)
- [How Well Do Sparse Imagenet Models Transfer?](https://mlsanity.com/paper/2111.13445/) (2021)
- [The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation](https://mlsanity.com/paper/2110.03036/) (2021)
- [Playing Lottery Tickets with Vision and Language](https://mlsanity.com/paper/2104.11832/) (2021)
- [ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity](https://mlsanity.com/paper/2208.02507/) (2022)
- [Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity](https://mlsanity.com/paper/2106.14568/) (2021)
- [Scaling Laws for Sparsely-Connected Foundation Models](https://mlsanity.com/paper/2309.08520/) (2023)
- [QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models](https://mlsanity.com/paper/2310.16795/) (2023)
- [Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm](https://mlsanity.com/paper/2104.08682/) (2021)
- [Dynamic Sparse Training with Structured Sparsity](https://mlsanity.com/paper/2305.02299/) (2023)
- [SPDY: Accurate Pruning with Speedup Guarantees](https://mlsanity.com/paper/2201.13096/) (2022)
- [SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models](https://mlsanity.com/paper/2303.10464/) (2023)
- [An Information-Theoretic Justification for Model Pruning](https://mlsanity.com/paper/2102.08329/) (2021)
- [Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researchers](https://mlsanity.com/paper/2302.02596/) (2023)
- [Post-training deep neural network pruning via layer-wise calibration](https://mlsanity.com/paper/2104.15023/) (2021)
- [The Elastic Lottery Ticket Hypothesis](https://mlsanity.com/paper/2103.16547/) (2021)
- [Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm](https://mlsanity.com/paper/2110.08190/) (2021)
- [Anytime Dense Prediction with Confidence Adaptivity](https://mlsanity.com/paper/2104.00749/) (2021)
- [Dynamic Sparsity Is Channel-Level Sparsity Learner](https://mlsanity.com/paper/2305.19454/) (2023)
- [Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers](https://mlsanity.com/paper/2402.04744/) (2024)

## Abstract (arXiv)

Historically, the pursuit of efficient inference has been one of the driving forces behind research into new deep learning architectures and building blocks. Some recent examples include: the squeeze-and-excitation module, depthwise separable convolutions in Xception, and the inverted bottleneck in MobileNet v2. Notably, in all of these cases, the resulting building blocks enabled not only higher efficiency, but also higher accuracy, and found wide adoption in the field. In this work, we further expand the arsenal of efficient building blocks for neural network architectures; but instead of combining standard primitives (such as convolution), we advocate for the replacement of these dense primitives with their sparse counterparts. While the idea of using sparsity to decrease the parameter count is not new, the conventional wisdom is that this reduction in theoretical FLOPs does not translate into real-world efficiency gains. We aim to correct this misconception by introducing a family of efficient sparse kernels for ARM and WebAssembly, which we open-source for the benefit of the community as part of the XNNPACK library. Equipped with our efficient implementation of sparse primitives, we show that sparse versions of MobileNet v1, MobileNet v2 and EfficientNet architectures substantially outperform strong dense baselines on the efficiency-accuracy curve. On Snapdragon 835 our sparse networks outperform their dense equivalents by 1.3-2.4× -- equivalent to approximately one entire generation of MobileNet-family improvement. We hope that our findings will facilitate wider adoption of sparsity as a tool for creating efficient and accurate deep learning architectures.