# A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation

arXiv: https://arxiv.org/abs/2403.03483 · HTML: https://mlsanity.com/paper/2403.03483/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Graph neural network distillation, one of 12 directions in Knowledge distillation.
- Builds on 48 of its 70 references that are in the map.
- First posted on arXiv 6 Mar 2024.

## Placed in

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

## Builds on (most cited first, 30 of 48)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [LINE: Large-scale Information Network Embedding](https://mlsanity.com/paper/1503.03578/) (2015)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [Towards Deeper Graph Neural Networks](https://mlsanity.com/paper/2007.09296/) (2020)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Training Graph Neural Networks with 1000 Layers](https://mlsanity.com/paper/2106.07476/) (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)
- [InfoGCL: Information-Aware Graph Contrastive Learning](https://mlsanity.com/paper/2110.15438/) (2021)

## Built on by (most cited first, 8 of 8)

- [Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation](https://mlsanity.com/paper/2407.14768/) (2024)
- [Simple yet Effective Graph Distillation via Clustering](https://mlsanity.com/paper/2505.20807/) (2025)
- [Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models](https://mlsanity.com/paper/2409.12512/) (2024)
- [Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference](https://mlsanity.com/paper/2411.14035/) (2024)
- [DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation](https://mlsanity.com/paper/2604.03154/) (2026)
- [Sparse Decomposition of Graph Neural Networks](https://mlsanity.com/paper/2410.19723/) (2024)
- [BPL: Bias-adaptive Preference Distillation Learning for Recommender System](https://mlsanity.com/paper/2510.16076/) (2025)
- [Heterogeneous Knowledge Distillation via Geometry Decoupling and Momentum-Aware Gradient Regulation](https://mlsanity.com/paper/2606.24557/) (2026)

## Abstract (arXiv)

Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical industrial applications. One reason for such an academic-industry gap is the neighborhood-fetching latency incurred by data dependency in GNNs. To reduce their gaps, Graph Knowledge Distillation (GKD) is proposed, usually based on a standard teacher-student architecture, to distill knowledge from a large teacher GNN into a lightweight student GNN or MLP. However, we found in this paper that neither teachers nor GNNs are necessary for graph knowledge distillation. We propose a Teacher-Free Graph Self-Distillation (TGS) framework that does not require any teacher model or GNNs during both training and inference. More importantly, the proposed TGS framework is purely based on MLPs, where structural information is only implicitly used to guide dual knowledge self-distillation between the target node and its neighborhood. As a result, TGS enjoys the benefits of graph topology awareness in training but is free from data dependency in inference. Extensive experiments have shown that the performance of vanilla MLPs can be greatly improved with dual self-distillation, e.g., TGS improves over vanilla MLPs by 15.54% on average and outperforms state-of-the-art GKD algorithms on six real-world datasets. In terms of inference speed, TGS infers 75X-89X faster than existing GNNs and 16X-25X faster than classical inference acceleration methods.