# The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains

arXiv: https://arxiv.org/abs/2205.11416 · HTML: https://mlsanity.com/paper/2205.11416/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 34 references that are in the map.
- First posted on arXiv 23 May 2022.

## Builds on (most cited first, 29 of 29)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [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)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Movement Pruning: Adaptive Sparsity by Fine-Tuning](https://mlsanity.com/paper/2005.07683/) (2020)
- [Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning](https://mlsanity.com/paper/2012.09816/) (2020)
- [R-Drop: Regularized Dropout for Neural Networks](https://mlsanity.com/paper/2106.14448/) (2021)
- [XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation](https://mlsanity.com/paper/2104.07412/) (2021)
- [SEED: Self-supervised Distillation For Visual Representation](https://mlsanity.com/paper/2101.04731/) (2021)
- [A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation](https://mlsanity.com/paper/1810.13243/) (2018)
- [Global Sparse Momentum SGD for Pruning Very Deep Neural Networks](https://mlsanity.com/paper/1909.12778/) (2019)
- [A Gradient Flow Framework For Analyzing Network Pruning](https://mlsanity.com/paper/2009.11839/) (2020)
- [The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/2002.07972/) (2020)
- [No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models](https://mlsanity.com/paper/2202.02664/) (2022)
- [Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization](https://mlsanity.com/paper/1812.00481/) (2018)
- [Por Qu'e N~ao Utiliser Alla Spraak? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer](https://mlsanity.com/paper/2204.13869/) (2022)

## Built on by (most cited first, 6 of 6)

- [Learning Task-Agnostic Representations through Multi-Teacher Distillation](https://mlsanity.com/paper/2510.18680/) (2025)
- [Condensing Multilingual Knowledge with Lightweight Language-Specific Modules](https://mlsanity.com/paper/2305.13993/) (2023)
- [KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization](https://mlsanity.com/paper/2505.19679/) (2025)
- [Language-Aware Multilingual Machine Translation with Self-Supervised Learning](https://mlsanity.com/paper/2302.05008/) (2023)
- [Neural Language Model Pruning for Automatic Speech Recognition](https://mlsanity.com/paper/2310.03424/) (2023)
- [SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios](https://mlsanity.com/paper/2508.04100/) (2025)

## Abstract (arXiv)

Recent model pruning methods have demonstrated the ability to remove redundant parameters without sacrificing model performance. Common methods remove redundant parameters according to the parameter sensitivity, a gradient-based measure reflecting the contribution of the parameters. In this paper, however, we argue that redundant parameters can be trained to make beneficial contributions. We first highlight the large sensitivity (contribution) gap among high-sensitivity and low-sensitivity parameters and show that the model generalization performance can be significantly improved after balancing the contribution of all parameters. Our goal is to balance the sensitivity of all parameters and encourage all of them to contribute equally. We propose a general task-agnostic method, namely intra-distillation, appended to the regular training loss to balance parameter sensitivity. Moreover, we also design a novel adaptive learning method to control the strength of intra-distillation loss for faster convergence. Our experiments show the strong effectiveness of our methods on machine translation, natural language understanding, and zero-shot cross-lingual transfer across up to 48 languages, e.g., a gain of 3.54 BLEU on average across 8 language pairs from the IWSLT'14 translation dataset.