# Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference

arXiv: https://arxiv.org/abs/2411.14035 · HTML: https://mlsanity.com/paper/2411.14035/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 51 references that are in the map.
- First posted on arXiv 21 Nov 2024.

## Builds on (most cited first, 30 of 33)

- [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)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation](https://mlsanity.com/paper/2110.08727/) (2021)
- [Heterogeneous Information Network Embedding for Recommendation](https://mlsanity.com/paper/1711.10730/) (2017)
- [Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning](https://mlsanity.com/paper/2105.09111/) (2021)
- [Relational Graph Attention Networks](https://mlsanity.com/paper/1904.05811/) (2019)
- [Interpretable and Efficient Heterogeneous Graph Convolutional Network](https://mlsanity.com/paper/2005.13183/) (2020)
- [Linkless Link Prediction via Relational Distillation](https://mlsanity.com/paper/2210.05801/) (2022)
- [VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs](https://mlsanity.com/paper/2308.02117/) (2023)
- [On Graph Neural Networks versus Graph-Augmented MLPs](https://mlsanity.com/paper/2010.15116/) (2020)
- [IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research](https://mlsanity.com/paper/2302.13522/) (2023)
- [Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator](https://mlsanity.com/paper/1911.10688/) (2019)
- [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)
- [Reliable Node Similarity Matrix Guided Contrastive Graph Clustering](https://mlsanity.com/paper/2408.03765/) (2024)
- [Deep Insights into Noisy Pseudo Labeling on Graph Data](https://mlsanity.com/paper/2310.01634/) (2023)
- [Joint embedding of structure and features via graph convolutional networks](https://mlsanity.com/paper/1905.08636/) (2019)
- [A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation](https://mlsanity.com/paper/2403.03483/) (2024)

## Built on by (most cited first, 2 of 2)

- [Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains](https://mlsanity.com/paper/2412.08937/) (2024)
- [Relational Database Distillation: From Structured Tables to Condensed Graph Data](https://mlsanity.com/paper/2510.06980/) (2025)

## Abstract (arXiv)

Heterogeneous Graph Neural Networks (HGNNs) have achieved promising results in various heterogeneous graph learning tasks, owing to their superiority in capturing the intricate relationships and diverse relational semantics inherent in heterogeneous graph structures. However, the neighborhood-fetching latency incurred by structure dependency in HGNNs makes it challenging to deploy for latency-constrained applications that require fast inference. Inspired by recent GNN-to-MLP knowledge distillation frameworks, we introduce HG2M and HG2M+ to combine both HGNN's superior performance and MLP's efficient inference. HG2M directly trains student MLPs with node features as input and soft labels from teacher HGNNs as targets, and HG2M+ further distills reliable and heterogeneous semantic knowledge into student MLPs through reliable node distillation and reliable meta-path distillation. Experiments conducted on six heterogeneous graph datasets show that despite lacking structural dependencies, HG2Ms can still achieve competitive or even better performance than HGNNs and significantly outperform vanilla MLPs. Moreover, HG2Ms demonstrate a 379.24× speedup in inference over HGNNs on the large-scale IGB-3M-19 dataset, showcasing their ability for latency-sensitive deployments.