# Multi-hop Attention Graph Neural Network

arXiv: https://arxiv.org/abs/2009.14332 · HTML: https://mlsanity.com/paper/2009.14332/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 30 of 53)

- [On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology](https://mlsanity.com/paper/2302.02941/) (2023)
- [How Powerful are K-hop Message Passing Graph Neural Networks](https://mlsanity.com/paper/2205.13328/) (2022)
- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs](https://mlsanity.com/paper/2305.12788/) (2023)
- [Locality-Aware Graph-Rewiring in GNNs](https://mlsanity.com/paper/2310.01668/) (2023)
- [Rewiring with Positional Encodings for Graph Neural Networks](https://mlsanity.com/paper/2201.12674/) (2022)
- [Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2305.12398/) (2023)
- [The Expressive Power of Graph Neural Networks: A Survey](https://mlsanity.com/paper/2308.08235/) (2023)
- [Towards Deep Attention in Graph Neural Networks: Problems and Remedies](https://mlsanity.com/paper/2306.02376/) (2023)
- [Over-Squashing in Graph Neural Networks: A Comprehensive survey](https://mlsanity.com/paper/2308.15568/) (2023)
- [Graph4MM: Weaving Multimodal Learning with Structural Information](https://mlsanity.com/paper/2510.16990/) (2025)
- [TraverseNet: Unifying Space and Time in Message Passing for Traffic Forecasting](https://mlsanity.com/paper/2109.02474/) (2021)
- [Decoupling Long- and Short-Term Patterns in Spatiotemporal Inference](https://mlsanity.com/paper/2109.09506/) (2021)
- [MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data](https://mlsanity.com/paper/2310.02275/) (2023)
- [Understanding Virtual Nodes: Oversquashing and Node Heterogeneity](https://mlsanity.com/paper/2405.13526/) (2024)
- [Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences](https://mlsanity.com/paper/2210.11794/) (2022)
- [Graph Convolutions Enrich the Self-Attention in Transformers!](https://mlsanity.com/paper/2312.04234/) (2023)
- [Attentive Walk-Aggregating Graph Neural Networks](https://mlsanity.com/paper/2110.02667/) (2021)
- [Improving the Expressiveness of K-hop Message-Passing GNNs by Injecting Contextualized Substructure Information](https://mlsanity.com/paper/2406.19244/) (2024)
- [Learnable Graph Convolutional Attention Networks](https://mlsanity.com/paper/2211.11853/) (2022)
- [Chain and Causal Attention for Efficient Entity Tracking](https://mlsanity.com/paper/2410.05565/) (2024)
- [Neuro-Symbolic Learning: Principles and Applications in Ophthalmology](https://mlsanity.com/paper/2208.00374/) (2022)
- [Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learning](https://mlsanity.com/paper/2210.07715/) (2022)
- [Order-Independence Without Fine Tuning](https://mlsanity.com/paper/2406.06581/) (2024)
- [A Survey of Link Prediction in Temporal Networks](https://mlsanity.com/paper/2502.21185/) (2025)
- [Tailoring Self-Attention for Graph via Rooted Subtrees](https://mlsanity.com/paper/2310.05296/) (2023)
- [Spiking GATs: Learning Graph Attentions via Spiking Neural Network](https://mlsanity.com/paper/2209.13539/) (2022)
- [Domain independent post-processing with graph U-nets: Applications to Electrical Impedance Tomographic Imaging](https://mlsanity.com/paper/2305.05020/) (2023)
- [Towards Label Position Bias in Graph Neural Networks](https://mlsanity.com/paper/2305.15822/) (2023)
- [DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text](https://mlsanity.com/paper/2310.12557/) (2023)

## Abstract (arXiv)

Self-attention mechanism in graph neural networks (GNNs) led to state-of-the-art performance on many graph representation learning tasks. Currently, at every layer, attention is computed between connected pairs of nodes and depends solely on the representation of the two nodes. However, such attention mechanism does not account for nodes that are not directly connected but provide important network context. Here we propose Multi-hop Attention Graph Neural Network (MAGNA), a principled way to incorporate multi-hop context information into every layer of attention computation. MAGNA diffuses the attention scores across the network, which increases the receptive field for every layer of the GNN. Unlike previous approaches, MAGNA uses a diffusion prior on attention values, to efficiently account for all paths between the pair of disconnected nodes. We demonstrate in theory and experiments that MAGNA captures large-scale structural information in every layer, and has a low-pass effect that eliminates noisy high-frequency information from graph data. Experimental results on node classification as well as the knowledge graph completion benchmarks show that MAGNA achieves state-of-the-art results: MAGNA achieves up to 5.7 percent relative error reduction over the previous state-of-the-art on Cora, Citeseer, and Pubmed. MAGNA also obtains the best performance on a large-scale Open Graph Benchmark dataset. On knowledge graph completion MAGNA advances state-of-the-art on WN18RR and FB15k-237 across four different performance metrics.