# Graph Pointer Neural Networks

arXiv: https://arxiv.org/abs/2110.00973 · HTML: https://mlsanity.com/paper/2110.00973/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 3 Oct 2021.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [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)
- [Rethinking Graph Transformers with Spectral Attention](https://mlsanity.com/paper/2106.03893/) (2021)
- [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](https://mlsanity.com/paper/1905.00067/) (2019)
- [Diffusion Improves Graph Learning](https://mlsanity.com/paper/1911.05485/) (2019)
- [Do Transformers Really Perform Bad for Graph Representation?](https://mlsanity.com/paper/2106.05234/) (2021)
- [struc2vec: Learning Node Representations from Structural Identity](https://mlsanity.com/paper/1704.03165/) (2017)
- [Graph Random Neural Network for Semi-Supervised Learning on Graphs](https://mlsanity.com/paper/2005.11079/) (2020)
- [Scaling Graph Neural Networks with Approximate PageRank](https://mlsanity.com/paper/2007.01570/) (2020)
- [Large-Scale Learnable Graph Convolutional Networks](https://mlsanity.com/paper/1808.03965/) (2018)
- [Non-Local Graph Neural Networks](https://mlsanity.com/paper/2005.14612/) (2020)
- [Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology](https://mlsanity.com/paper/1907.05008/) (2019)
- [Deep Constraint-based Propagation in Graph Neural Networks](https://mlsanity.com/paper/2005.02392/) (2020)
- [Node2Seq: Towards Trainable Convolutions in Graph Neural Networks](https://mlsanity.com/paper/2101.01849/) (2021)

## Built on by (most cited first, 27 of 27)

- [Graph Neural Networks for Graphs with Heterophily: A Survey](https://mlsanity.com/paper/2202.07082/) (2022)
- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [Partitioning Message Passing for Graph Fraud Detection](https://mlsanity.com/paper/2412.00020/) (2024)
- [Understanding Heterophily for Graph Neural Networks](https://mlsanity.com/paper/2401.09125/) (2024)
- [Boosting Graph Structure Learning with Dummy Nodes](https://mlsanity.com/paper/2206.08561/) (2022)
- [A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions](https://mlsanity.com/paper/2401.09769/) (2024)
- [SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning](https://mlsanity.com/paper/2406.11389/) (2024)
- [SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation](https://mlsanity.com/paper/2305.09958/) (2023)
- [GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy](https://mlsanity.com/paper/2312.09708/) (2023)
- [Heterophily-Aware Graph Attention Network](https://mlsanity.com/paper/2302.03228/) (2023)
- [Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification](https://mlsanity.com/paper/2302.09755/) (2023)
- [Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection](https://mlsanity.com/paper/2407.02143/) (2024)
- [The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs](https://mlsanity.com/paper/2406.12539/) (2024)
- [A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects](https://mlsanity.com/paper/2309.01194/) (2023)
- [Learning to Branch in Combinatorial Optimization with Graph Pointer Networks](https://mlsanity.com/paper/2307.01434/) (2023)
- [Disambiguated Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2402.08824/) (2024)
- [Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning](https://mlsanity.com/paper/2308.08823/) (2023)
- [CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph](https://mlsanity.com/paper/2312.08672/) (2023)
- [A Bird's-Eye Tutorial of Graph Attention Architectures](https://mlsanity.com/paper/2206.02849/) (2022)
- [FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs](https://mlsanity.com/paper/2504.21206/) (2025)
- [DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data](https://mlsanity.com/paper/2605.03430/) (2026)
- [HGFormer: A Hierarchical Graph Transformer Framework for Two-Stage Colonel Blotto Games via Reinforcement Learning](https://mlsanity.com/paper/2506.08580/) (2025)
- [Aggregation-aware MLP: An Unsupervised Approach for Graph Message-passing](https://mlsanity.com/paper/2507.20127/) (2025)
- [Learning to Design City-scale Transit Routes](https://mlsanity.com/paper/2512.19767/) (2025)
- [Generating Diverse TSP Tours via a Combination of Graph Pointer Network and Dispersion](https://mlsanity.com/paper/2601.01132/) (2026)
- [CO-MAP: A Reinforcement Learning Approach to the Qubit Allocation Problem](https://mlsanity.com/paper/2605.13638/) (2026)
- [AlphaTransit: Learning to Design City-scale Transit Routes](https://mlsanity.com/paper/2605.28730/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have shown advantages in various graph-based applications. Most existing GNNs assume strong homophily of graph structure and apply permutation-invariant local aggregation of neighbors to learn a representation for each node. However, they fail to generalize to heterophilic graphs, where most neighboring nodes have different labels or features, and the relevant nodes are distant. Few recent studies attempt to address this problem by combining multiple hops of hidden representations of central nodes (i.e., multi-hop-based approaches) or sorting the neighboring nodes based on attention scores (i.e., ranking-based approaches). As a result, these approaches have some apparent limitations. On the one hand, multi-hop-based approaches do not explicitly distinguish relevant nodes from a large number of multi-hop neighborhoods, leading to a severe over-smoothing problem. On the other hand, ranking-based models do not joint-optimize node ranking with end tasks and result in sub-optimal solutions. In this work, we present Graph Pointer Neural Networks (GPNN) to tackle the challenges mentioned above. We leverage a pointer network to select the most relevant nodes from a large amount of multi-hop neighborhoods, which constructs an ordered sequence according to the relationship with the central node. 1D convolution is then applied to extract high-level features from the node sequence. The pointer-network-based ranker in GPNN is joint-optimized with other parts in an end-to-end manner. Extensive experiments are conducted on six public node classification datasets with heterophilic graphs. The results show that GPNN significantly improves the classification performance of state-of-the-art methods. In addition, analyses also reveal the privilege of the proposed GPNN in filtering out irrelevant neighbors and reducing over-smoothing.