# Neighbor Overlay-Induced Graph Attention Network

arXiv: https://arxiv.org/abs/2408.08788 · HTML: https://mlsanity.com/paper/2408.08788/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 84 references that are in the map.
- First posted on arXiv 16 Aug 2024.

## Builds on (most cited first, 9 of 9)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Beyond Low-frequency Information in Graph Convolutional Networks](https://mlsanity.com/paper/2101.00797/) (2021)
- [Learning to Drop: Robust Graph Neural Network via Topological Denoising](https://mlsanity.com/paper/2011.07057/) (2020)
- [Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction](https://mlsanity.com/paper/2206.04216/) (2022)
- [Learning Conjoint Attentions for Graph Neural Nets](https://mlsanity.com/paper/2102.03147/) (2021)
- [Learning Strong Graph Neural Networks with Weak Information](https://mlsanity.com/paper/2305.18457/) (2023)

## Built on by (most cited first, 1 of 1)

- [High-order Graph Neural Networks with Common Neighbor Awareness for Link Prediction](https://mlsanity.com/paper/2504.18758/) (2025)

## Abstract (arXiv)

Graph neural networks (GNNs) have garnered significant attention due to their ability to represent graph data. Among various GNN variants, graph attention network (GAT) stands out since it is able to dynamically learn the importance of different nodes. However, present GATs heavily rely on the smoothed node features to obtain the attention coefficients rather than graph structural information, which fails to provide crucial contextual cues for node representations. To address this issue, this study proposes a neighbor overlay-induced graph attention network (NO-GAT) with the following two-fold ideas: a) learning favorable structural information, i.e., overlaid neighbors, outside the node feature propagation process from an adjacency matrix; b) injecting the information of overlaid neighbors into the node feature propagation process to compute the attention coefficient jointly. Empirical studies on graph benchmark datasets indicate that the proposed NO-GAT consistently outperforms state-of-the-art models.