# Policy-GNN: Aggregation Optimization for Graph Neural Networks

arXiv: https://arxiv.org/abs/2006.15097 · HTML: https://mlsanity.com/paper/2006.15097/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2020.

## Built on by (most cited first, 30 of 48)

- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [Not too little, not too much: a theoretical analysis of graph (over)smoothing](https://mlsanity.com/paper/2205.12156/) (2022)
- [BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs](https://mlsanity.com/paper/2206.10071/) (2022)
- [Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing](https://mlsanity.com/paper/2302.01524/) (2023)
- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [Search to aggregate neighborhood for graph neural network](https://mlsanity.com/paper/2104.06608/) (2021)
- [Node Dependent Local Smoothing for Scalable Graph Learning](https://mlsanity.com/paper/2110.14377/) (2021)
- [Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks](https://mlsanity.com/paper/2104.07886/) (2021)
- [Pooling Architecture Search for Graph Classification](https://mlsanity.com/paper/2108.10587/) (2021)
- [Cooperative Graph Neural Networks](https://mlsanity.com/paper/2310.01267/) (2023)
- [FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks](https://mlsanity.com/paper/2206.06561/) (2022)
- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [Reinforcement learning on graphs: A survey](https://mlsanity.com/paper/2204.06127/) (2022)
- [RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search](https://mlsanity.com/paper/2206.06757/) (2022)
- [Graph Sparsification via Mixture of Graphs](https://mlsanity.com/paper/2405.14260/) (2024)
- [ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting](https://mlsanity.com/paper/2205.13700/) (2022)
- [Deep reinforcement learning guided graph neural networks for brain network analysis](https://mlsanity.com/paper/2203.10093/) (2022)
- [MAG-GNN: Reinforcement Learning Boosted Graph Neural Network](https://mlsanity.com/paper/2310.19142/) (2023)
- [Towards Adaptive Neighborhood for Advancing Temporal Interaction Graph Modeling](https://mlsanity.com/paper/2406.11891/) (2024)
- [Unsupervised Resource Allocation with Graph Neural Networks](https://mlsanity.com/paper/2106.09761/) (2021)
- [AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2301.03049/) (2023)
- [Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification](https://mlsanity.com/paper/2302.08671/) (2023)
- [Reinforcement Neighborhood Selection for Unsupervised Graph Anomaly Detection](https://mlsanity.com/paper/2312.05526/) (2023)
- [MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning](https://mlsanity.com/paper/2206.09280/) (2022)
- [Automated Graph Learning via Population Based Self-Tuning GCN](https://mlsanity.com/paper/2107.04713/) (2021)
- [Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models](https://mlsanity.com/paper/2305.01868/) (2023)
- [Combinatorial Optimization with Automated Graph Neural Networks](https://mlsanity.com/paper/2406.02872/) (2024)
- [Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction](https://mlsanity.com/paper/2411.01535/) (2024)
- [HybridGNN: Learning Hybrid Representation in Multiplex Heterogeneous Networks](https://mlsanity.com/paper/2208.02068/) (2022)
- [Edge-featured Graph Neural Architecture Search](https://mlsanity.com/paper/2109.01356/) (2021)

## Abstract (arXiv)

Graph data are pervasive in many real-world applications. Recently, increasing attention has been paid on graph neural networks (GNNs), which aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors with stackable network modules. Motivated by the observation that different nodes often require different iterations of aggregation to fully capture the structural information, in this paper, we propose to explicitly sample diverse iterations of aggregation for different nodes to boost the performance of GNNs. It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features. Moreover, it is not straightforward to derive an efficient algorithm since we need to feed the sampled nodes into different number of network layers. To address the above challenges, we propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process. Specifically, Policy-GNN uses a meta-policy to adaptively determine the number of aggregations for each node. The meta-policy is trained with deep reinforcement learning (RL) by exploiting the feedback from the model. We further introduce parameter sharing and a buffer mechanism to boost the training efficiency. Experimental results on three real-world benchmark datasets suggest that Policy-GNN significantly outperforms the state-of-the-art alternatives, showing the promise in aggregation optimization for GNNs.