# Scalable Graph Neural Networks for Heterogeneous Graphs

arXiv: https://arxiv.org/abs/2011.09679 · HTML: https://mlsanity.com/paper/2011.09679/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 30 of 31)

- [GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings](https://mlsanity.com/paper/2106.05609/) (2021)
- [Graph Attention Multi-Layer Perceptron](https://mlsanity.com/paper/2206.04355/) (2022)
- [Simple and Efficient Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2207.02547/) (2022)
- [Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training](https://mlsanity.com/paper/2104.09376/) (2021)
- [Multiplex Heterogeneous Graph Convolutional Network](https://mlsanity.com/paper/2208.06129/) (2022)
- [Large-scale graph representation learning with very deep GNNs and self-supervision](https://mlsanity.com/paper/2107.09422/) (2021)
- [Efficient Heterogeneous Graph Learning via Random Projection](https://mlsanity.com/paper/2310.14481/) (2023)
- [RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations](https://mlsanity.com/paper/2210.10737/) (2022)
- [SCR: Training Graph Neural Networks with Consistency Regularization](https://mlsanity.com/paper/2112.04319/) (2021)
- [Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials](https://mlsanity.com/paper/2305.19872/) (2023)
- [Simplifying Distributed Neural Network Training on Massive Graphs: Randomized Partitions Improve Model Aggregation](https://mlsanity.com/paper/2305.09887/) (2023)
- [MultiBiSage: A Web-Scale Recommendation System Using Multiple Bipartite Graphs at Pinterest](https://mlsanity.com/paper/2205.10666/) (2022)
- [Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modeling](https://mlsanity.com/paper/2403.05752/) (2024)
- [MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2211.12792/) (2022)
- [Long-range Meta-path Search on Large-scale Heterogeneous Graphs](https://mlsanity.com/paper/2307.08430/) (2023)
- [Graph Attention MLP with Reliable Label Utilization](https://mlsanity.com/paper/2108.10097/) (2021)
- [Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph](https://mlsanity.com/paper/2305.10771/) (2023)
- [HeteGraph-Mamba: Heterogeneous Graph Learning via Selective State Space Model](https://mlsanity.com/paper/2405.13915/) (2024)
- [Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation](https://mlsanity.com/paper/2110.06290/) (2021)
- [Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs](https://mlsanity.com/paper/2504.13266/) (2025)
- [ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion](https://mlsanity.com/paper/2504.15920/) (2025)
- [Dimensionality Reduction Meets Message Passing for Graph Node Embeddings](https://mlsanity.com/paper/2202.00408/) (2022)
- [Meta-multigraph Search: Rethinking Meta-structure on Heterogeneous Information Networks](https://mlsanity.com/paper/2304.11574/) (2023)
- [Heterogeneous Graph Neural Network on Semantic Tree](https://mlsanity.com/paper/2402.13496/) (2024)
- [Training-free Heterogeneous Graph Condensation via Data Selection](https://mlsanity.com/paper/2412.16250/) (2024)
- [Bridging RDF Knowledge Graphs with Graph Neural Networks for Semantically-Rich Recommender Systems](https://mlsanity.com/paper/2506.08743/) (2025)
- [CITE: A Comprehensive Benchmark for Heterogeneous Text-Attributed Graphs on Catalytic Materials](https://mlsanity.com/paper/2508.15392/) (2025)
- [Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning](https://mlsanity.com/paper/2511.11081/) (2025)
- [Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphs](https://mlsanity.com/paper/2406.14142/) (2024)
- [Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts](https://mlsanity.com/paper/2601.05537/) (2026)

## Abstract (arXiv)

Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data. Recent work has argued that GNNs primarily use the graph for feature smoothing, and have shown competitive results on benchmark tasks by simply operating on graph-smoothed node features, rather than using end-to-end learned feature hierarchies that are challenging to scale to large graphs. In this work, we ask whether these results can be extended to heterogeneous graphs, which encode multiple types of relationship between different entities. We propose Neighbor Averaging over Relation Subgraphs (NARS), which trains a classifier on neighbor-averaged features for randomly-sampled subgraphs of the "metagraph" of relations. We describe optimizations to allow these sets of node features to be computed in a memory-efficient way, both at training and inference time. NARS achieves a new state of the art accuracy on several benchmark datasets, outperforming more expensive GNN-based methods