# Unified and Effective Ensemble Knowledge Distillation

arXiv: https://arxiv.org/abs/2204.00548 · HTML: https://mlsanity.com/paper/2204.00548/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 1 Apr 2022.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 20 of 20)

- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning](https://mlsanity.com/paper/2012.09816/) (2020)
- [Knowledge Distillation by On-the-Fly Native Ensemble](https://mlsanity.com/paper/1806.04606/) (2018)
- [Data Distillation: Towards Omni-Supervised Learning](https://mlsanity.com/paper/1712.04440/) (2017)
- [Improving model calibration with accuracy versus uncertainty optimization](https://mlsanity.com/paper/2012.07923/) (2020)
- [One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers](https://mlsanity.com/paper/2106.01023/) (2021)
- [Ensemble Distillation for Neural Machine Translation](https://mlsanity.com/paper/1702.01802/) (2017)
- [Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding](https://mlsanity.com/paper/1904.09482/) (2019)
- [Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion](https://mlsanity.com/paper/1904.03446/) (2019)
- [Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation](https://mlsanity.com/paper/2002.10345/) (2020)
- [FEED: Feature-level Ensemble for Knowledge Distillation](https://mlsanity.com/paper/1909.10754/) (2019)
- [Online Ensemble Model Compression using Knowledge Distillation](https://mlsanity.com/paper/2011.07449/) (2020)

## Built on by (most cited first, 5 of 5)

- [PROD: Progressive Distillation for Dense Retrieval](https://mlsanity.com/paper/2209.13335/) (2022)
- [Ensemble knowledge distillation of self-supervised speech models](https://mlsanity.com/paper/2302.12757/) (2023)
- [LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives](https://mlsanity.com/paper/2407.01490/) (2024)
- [MIND: Modality-Informed Knowledge Distillation Framework for Multimodal Clinical Prediction Tasks](https://mlsanity.com/paper/2502.01158/) (2025)
- [GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillation](https://mlsanity.com/paper/2405.03764/) (2024)

## Abstract (arXiv)

Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are usually learned on the same labeled data, and their predictions have high correlations with groudtruth labels. Thus, they cannot provide sufficient knowledge complementary to task labels for student teaching. Distilling on unseen unlabeled data has the potential to enhance the knowledge transfer from the teachers to the student. In this paper, we propose a unified and effective ensemble knowledge distillation method that distills a single student model from an ensemble of teacher models on both labeled and unlabeled data. Since different teachers may have diverse prediction correctness on the same sample, on labeled data we weight the predictions of different teachers according to their correctness. In addition, we weight the distillation loss based on the overall prediction correctness of the teacher ensemble to distill high-quality knowledge. On unlabeled data, there is no groundtruth to evaluate prediction correctness. Fortunately, the disagreement among teachers is an indication of sample hardness, and thereby we weight the distillation loss based on teachers' disagreement to emphasize knowledge distillation on important samples. Extensive experiments on four datasets show the effectiveness of our proposed ensemble distillation method.