# SEVEN: Pruning Transformer Model by Reserving Sentinels

arXiv: https://arxiv.org/abs/2403.12688 · HTML: https://mlsanity.com/paper/2403.12688/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [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)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model](https://mlsanity.com/paper/2201.11990/) (2022)
- [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)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [Movement Pruning: Adaptive Sparsity by Fine-Tuning](https://mlsanity.com/paper/2005.07683/) (2020)
- [The Lottery Ticket Hypothesis for Pre-trained BERT Networks](https://mlsanity.com/paper/2007.12223/) (2020)
- [A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks](https://mlsanity.com/paper/1901.06053/) (2019)
- [Structured Pruning of Large Language Models](https://mlsanity.com/paper/1910.04732/) (2019)
- [Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02934/) (2021)
- [Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning](https://mlsanity.com/paper/2002.08307/) (2020)
- [Structured Pruning Learns Compact and Accurate Models](https://mlsanity.com/paper/2204.00408/) (2022)
- [Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks](https://mlsanity.com/paper/1903.11680/) (2019)
- [Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning](https://mlsanity.com/paper/2010.05627/) (2020)
- [When BERT Plays the Lottery, All Tickets Are Winning](https://mlsanity.com/paper/2005.00561/) (2020)

## Abstract (arXiv)

Large-scale Transformer models (TM) have demonstrated outstanding performance across various tasks. However, their considerable parameter size restricts their applicability, particularly on mobile devices. Due to the dynamic and intricate nature of gradients on TM compared to Convolutional Neural Networks, commonly used pruning methods tend to retain weights with larger gradient noise. This results in pruned models that are sensitive to sparsity and datasets, exhibiting suboptimal performance. Symbolic Descent (SD) is a general approach for training and fine-tuning TM. In this paper, we attempt to describe the noisy batch gradient sequences on TM through the cumulative process of SD. We utilize this design to dynamically assess the importance scores of weights.SEVEN is introduced by us, which particularly favors weights with consistently high sensitivity, i.e., weights with small gradient noise. These weights are tended to be preserved by SEVEN. Extensive experiments on various TM in natural language, question-answering, and image classification domains are conducted to validate the effectiveness of SEVEN. The results demonstrate significant improvements of SEVEN in multiple pruning scenarios and across different sparsity levels. Additionally, SEVEN exhibits robust performance under various fine-tuning strategies. The code is publicly available at https://github.com/xiaojinying/SEVEN.