# Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation

arXiv: https://arxiv.org/abs/2407.14768 · HTML: https://mlsanity.com/paper/2407.14768/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Graph neural network distillation, one of 12 directions in Knowledge distillation.
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 20 Jul 2024.

## Placed in

- Knowledge distillation / [Graph neural network distillation](https://mlsanity.com/distill/graph-neural-network-distillation/)

## Builds on (most cited first, 27 of 27)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](https://mlsanity.com/paper/1905.00067/) (2019)
- [Does Knowledge Distillation Really Work?](https://mlsanity.com/paper/2106.05945/) (2021)
- [Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation](https://mlsanity.com/paper/2110.08727/) (2021)
- [Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive](https://mlsanity.com/paper/2105.07342/) (2021)
- [Distilling Knowledge from Graph Convolutional Networks](https://mlsanity.com/paper/2003.10477/) (2020)
- [Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective](https://mlsanity.com/paper/2102.00650/) (2021)
- [Densely Guided Knowledge Distillation using Multiple Teacher Assistants](https://mlsanity.com/paper/2009.08825/) (2020)
- [Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework](https://mlsanity.com/paper/2103.02885/) (2021)
- [Annealing Knowledge Distillation](https://mlsanity.com/paper/2104.07163/) (2021)
- [Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study](https://mlsanity.com/paper/2104.00676/) (2021)
- [Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation](https://mlsanity.com/paper/2206.06067/) (2022)
- [On Self-Distilling Graph Neural Network](https://mlsanity.com/paper/2011.02255/) (2020)
- [Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs](https://mlsanity.com/paper/2306.05628/) (2023)
- [Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework](https://mlsanity.com/paper/2305.10758/) (2023)
- [FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks](https://mlsanity.com/paper/2206.06561/) (2022)
- [Iterative Graph Self-Distillation](https://mlsanity.com/paper/2010.12609/) (2020)
- [Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation](https://mlsanity.com/paper/2205.11678/) (2022)
- [Multi-task Self-distillation for Graph-based Semi-Supervised Learning](https://mlsanity.com/paper/2112.01174/) (2021)
- [A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation](https://mlsanity.com/paper/2403.03483/) (2024)

## Built on by (most cited first, 4 of 4)

- [ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs](https://mlsanity.com/paper/2507.19031/) (2025)
- [InfGraND: An Influence-Guided GNN-to-MLP Knowledge Distillation](https://mlsanity.com/paper/2601.08033/) (2026)
- [Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction](https://mlsanity.com/paper/2504.06193/) (2025)
- [Diffusion-Assisted Distillation for Self-Supervised Graph Representation Learning with MLPs](https://mlsanity.com/paper/2510.04241/) (2025)

## Abstract (arXiv)

To bridge the gaps between powerful Graph Neural Networks (GNNs) and lightweight Multi-Layer Perceptron (MLPs), GNN-to-MLP Knowledge Distillation (KD) proposes to distill knowledge from a well-trained teacher GNN into a student MLP. In this paper, we revisit the knowledge samples (nodes) in teacher GNNs from the perspective of hardness, and identify that hard sample distillation may be a major performance bottleneck of existing graph KD algorithms. The GNN-to-MLP KD involves two different types of hardness, one student-free knowledge hardness describing the inherent complexity of GNN knowledge, and the other student-dependent distillation hardness describing the difficulty of teacher-to-student distillation. However, most of the existing work focuses on only one of these aspects or regards them as one thing. This paper proposes a simple yet effective Hardness-aware GNN-to-MLP Distillation (HGMD) framework, which decouples the two hardnesses and estimates them using a non-parametric approach. Finally, two hardness-aware distillation schemes (i.e., HGMD-weight and HGMD-mixup) are further proposed to distill hardness-aware knowledge from teacher GNNs into the corresponding nodes of student MLPs. As non-parametric distillation, HGMD does not involve any additional learnable parameters beyond the student MLPs, but it still outperforms most of the state-of-the-art competitors. HGMD-mixup improves over the vanilla MLPs by 12.95% and outperforms its teacher GNNs by 2.48% averaged over seven real-world datasets.