# Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification

arXiv: https://arxiv.org/abs/2201.01381 · HTML: https://mlsanity.com/paper/2201.01381/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 64 references that are in the map.
- First posted on arXiv 4 Jan 2022.

## Builds on (most cited first, 30 of 32)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Understanding over-squashing and bottlenecks on graphs via curvature](https://mlsanity.com/paper/2111.14522/) (2021)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks](https://mlsanity.com/paper/2102.06462/) (2021)
- [Graph-Bert: Only Attention is Needed for Learning Graph Representations](https://mlsanity.com/paper/2001.05140/) (2020)
- [GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs](https://mlsanity.com/paper/1803.07294/) (2018)
- [Directed Graph Convolutional Network](https://mlsanity.com/paper/2004.13970/) (2020)
- [Gated Graph Recurrent Neural Networks](https://mlsanity.com/paper/2002.01038/) (2020)
- [GraphNAS: Graph Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1904.09981/) (2019)
- [Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs](https://mlsanity.com/paper/2004.13465/) (2020)
- [Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version](https://mlsanity.com/paper/2103.10760/) (2021)
- [Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation](https://mlsanity.com/paper/1606.04429/) (2016)
- [WGCN: Graph Convolutional Networks with Weighted Structural Features](https://mlsanity.com/paper/2104.14060/) (2021)
- [Graph Star Net for Generalized Multi-Task Learning](https://mlsanity.com/paper/1906.12330/) (2019)
- [Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages](https://mlsanity.com/paper/2106.08541/) (2021)
- [Cleora: A Simple, Strong and Scalable Graph Embedding Scheme](https://mlsanity.com/paper/2102.02302/) (2021)
- [FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping](https://mlsanity.com/paper/2110.11464/) (2021)

## Abstract (arXiv)

Graph neural networks can be effectively applied to find solutions for many real-world problems across widely diverse fields. The success of graph neural networks is linked to the message-passing mechanism on the graph, however, the message-aggregating behavior is still not entirely clear in most algorithms. To improve functionality, we propose a new transparent network called Graph Decipher to investigate the message-passing mechanism by prioritizing in two main components: the graph structure and node attributes, at the graph, feature, and global levels on a graph under the node classification task. However, the computation burden now becomes the most significant issue because the relevance of both graph structure and node attributes are computed on a graph. In order to solve this issue, only relevant representative node attributes are extracted by graph feature filters, allowing calculations to be performed in a category-oriented manner. Experiments on seven datasets show that Graph Decipher achieves state-of-the-art performance while imposing a substantially lower computation burden under the node classification task. Additionally, since our algorithm has the ability to explore the representative node attributes by category, it is utilized to alleviate the imbalanced node classification problem on multi-class graph datasets.