# Teacher as a Lenient Expert: Teacher-Agnostic Data-Free Knowledge Distillation

arXiv: https://arxiv.org/abs/2402.12406 · HTML: https://mlsanity.com/paper/2402.12406/

## 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 19 of its 26 references that are in the map.
- First posted on arXiv 18 Feb 2024.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Decoupling "when to update" from "how to update"](https://mlsanity.com/paper/1706.02613/) (2017)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [Zero-shot Knowledge Transfer via Adversarial Belief Matching](https://mlsanity.com/paper/1905.09768/) (2019)
- [Zero-Shot Knowledge Distillation in Deep Networks](https://mlsanity.com/paper/1905.08114/) (2019)
- [Data-Free Adversarial Distillation](https://mlsanity.com/paper/1912.11006/) (2019)
- [Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data](https://mlsanity.com/paper/2108.05698/) (2021)
- [Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation](https://mlsanity.com/paper/2209.10359/) (2022)
- [Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation](https://mlsanity.com/paper/2302.14290/) (2023)
- [Revisiting Data-Free Knowledge Distillation with Poisoned Teachers](https://mlsanity.com/paper/2306.02368/) (2023)
- [Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy](https://mlsanity.com/paper/2208.13648/) (2022)

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

- [Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environments](https://mlsanity.com/paper/2505.19699/) (2025)
- [Distilling A Universal Expert from Clustered Federated Learning](https://mlsanity.com/paper/2506.20285/) (2025)
- [TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins](https://mlsanity.com/paper/2603.15481/) (2026)
- [InFiConD: Interactive No-code Fine-tuning with Concept-based Knowledge Distillation](https://mlsanity.com/paper/2406.17838/) (2024)
- [On the Failure of Boundary-Seeking Distillation in Bottlenecked Generative Architectures](https://mlsanity.com/paper/2607.15919/) (2026)

## Abstract (arXiv)

Data-free knowledge distillation (DFKD) aims to distill pretrained knowledge to a student model with the help of a generator without using original data. In such data-free scenarios, achieving stable performance of DFKD is essential due to the unavailability of validation data. Unfortunately, this paper has discovered that existing DFKD methods are quite sensitive to different teacher models, occasionally showing catastrophic failures of distillation, even when using well-trained teacher models. Our observation is that the generator in DFKD is not always guaranteed to produce precise yet diverse samples using the existing representative strategy of minimizing both class-prior and adversarial losses. Through our empirical study, we focus on the fact that class-prior not only decreases the diversity of generated samples, but also cannot completely address the problem of generating unexpectedly low-quality samples depending on teacher models. In this paper, we propose the teacher-agnostic data-free knowledge distillation (TA-DFKD) method, with the goal of more robust and stable performance regardless of teacher models. Our basic idea is to assign the teacher model a lenient expert role for evaluating samples, rather than a strict supervisor that enforces its class-prior on the generator. Specifically, we design a sample selection approach that takes only clean samples verified by the teacher model without imposing restrictions on the power of generating diverse samples. Through extensive experiments, we show that our method successfully achieves both robustness and training stability across various teacher models, while outperforming the existing DFKD methods.