# Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researchers

arXiv: https://arxiv.org/abs/2302.02596 · HTML: https://mlsanity.com/paper/2302.02596/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 81 of its 110 references that are in the map.
- First posted on arXiv 6 Feb 2023.

## Builds on (most cited first, 30 of 81)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Deep Learning Scaling is Predictable, Empirically](https://mlsanity.com/paper/1712.00409/) (2017)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)

## Built on by (most cited first, 25 of 25)

- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity](https://mlsanity.com/paper/2310.05175/) (2023)
- [KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches](https://mlsanity.com/paper/2407.01527/) (2024)
- [No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models](https://mlsanity.com/paper/2307.06440/) (2023)
- [Visual Tuning](https://mlsanity.com/paper/2305.06061/) (2023)
- [Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!](https://mlsanity.com/paper/2303.02141/) (2023)
- [E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation](https://mlsanity.com/paper/2312.04727/) (2023)
- [JaxPruner: A concise library for sparsity research](https://mlsanity.com/paper/2304.14082/) (2023)
- [Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness](https://mlsanity.com/paper/2410.03030/) (2024)
- [Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness](https://mlsanity.com/paper/2409.01249/) (2024)
- [Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates](https://mlsanity.com/paper/2308.14831/) (2023)
- [A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness](https://mlsanity.com/paper/2309.03004/) (2023)
- [Efficient Model Compression Techniques with FishLeg](https://mlsanity.com/paper/2412.02328/) (2024)
- [Dynamic Sparse Training of Diagonally Sparse Networks](https://mlsanity.com/paper/2506.11449/) (2025)
- [Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization](https://mlsanity.com/paper/2406.01755/) (2024)
- [Navigating Extremes: Dynamic Sparsity in Large Output Spaces](https://mlsanity.com/paper/2411.03171/) (2024)
- [Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity](https://mlsanity.com/paper/2502.01330/) (2025)
- [Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers](https://mlsanity.com/paper/2305.18382/) (2023)
- [Importance Estimation with Random Gradient for Neural Network Pruning](https://mlsanity.com/paper/2310.20203/) (2023)
- [A Neural Network Alternative to Tree-based Models](https://mlsanity.com/paper/2410.17758/) (2024)
- [Vision Transformers for Mobile Applications: A Short Survey](https://mlsanity.com/paper/2305.19365/) (2023)
- [Neural Network Pruning for Real-time Polyp Segmentation](https://mlsanity.com/paper/2306.13203/) (2023)
- [Sparse-ProxSkip: Accelerated Sparse-to-Sparse Training in Federated Learning](https://mlsanity.com/paper/2405.20623/) (2024)
- [Batch Matrix-form Equations and Implementation of Multilayer Perceptrons](https://mlsanity.com/paper/2511.11918/) (2025)
- [Exploring the impact of adaptive rewiring in Graph Neural Networks](https://mlsanity.com/paper/2602.10754/) (2026)

## Abstract (arXiv)

This article does not propose any novel algorithm or new hardware for sparsity. Instead, it aims to serve the "common good" for the increasingly prosperous Sparse Neural Network (SNN) research community. We attempt to summarize some most common confusions in SNNs, that one may come across in various scenarios such as paper review/rebuttal and talks - many drawn from the authors' own bittersweet experiences! We feel that doing so is meaningful and timely, since the focus of SNN research is notably shifting from traditional pruning to more diverse and profound forms of sparsity before, during, and after training. The intricate relationships between their scopes, assumptions, and approaches lead to misunderstandings, for non-experts or even experts in SNNs. In response, we summarize ten Q&As of SNNs from many key aspects, including dense vs. sparse, unstructured sparse vs. structured sparse, pruning vs. sparse training, dense-to-sparse training vs. sparse-to-sparse training, static sparsity vs. dynamic sparsity, before-training/during-training vs. post-training sparsity, and many more. We strive to provide proper and generically applicable answers to clarify those confusions to the best extent possible. We hope our summary provides useful general knowledge for people who want to enter and engage with this exciting community; and also provides some "mind of ease" convenience for SNN researchers to explain their work in the right contexts. At the very least (and perhaps as this article's most insignificant target functionality), if you are writing/planning to write a paper or rebuttal in the field of SNNs, we hope some of our answers could help you!