# Hop-Hop Relation-aware Graph Neural Networks

arXiv: https://arxiv.org/abs/2012.11147 · HTML: https://mlsanity.com/paper/2012.11147/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

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

- [Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation](https://mlsanity.com/paper/2108.07181/) (2021)
- [HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization](https://mlsanity.com/paper/2110.06388/) (2021)
- [Relational Graph Neural Network Design via Progressive Neural Architecture Search](https://mlsanity.com/paper/2105.14490/) (2021)
- [Learning Robust Heterogeneous Graph Representations via Contrastive-Reconstruction under Sparse Semantics](https://mlsanity.com/paper/2506.06682/) (2025)
- [STN-TGAT: Top-K Portfolio Construction via Prior-Guided Graph Attention with Learnable Soft-Threshold Sparsification](https://mlsanity.com/paper/2607.19385/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) are widely used in graph representation learning. However, most GNN methods are designed for either homogeneous or heterogeneous graphs. In this paper, we propose a new model, Hop-Hop Relation-aware Graph Neural Network (HHR-GNN), to unify representation learning for these two types of graphs. HHR-GNN learns a personalized receptive field for each node by leveraging knowledge graph embedding to learn relation scores between the central node's representations at different hops. In neighborhood aggregation, our model simultaneously allows for hop-aware projection and aggregation. This mechanism enables the central node to learn a hop-wise neighborhood mixing that can be applied to both homogeneous and heterogeneous graphs. Experimental results on five benchmarks show the competitive performance of our model compared to state-of-the-art GNNs, e.g., up to 13K faster in terms of time cost per training epoch on large heterogeneous graphs.