# Adaptive Propagation Graph Convolutional Network

arXiv: https://arxiv.org/abs/2002.10306 · HTML: https://mlsanity.com/paper/2002.10306/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2020.

## Built on by (most cited first, 30 of 31)

- [Graph Attention Multi-Layer Perceptron](https://mlsanity.com/paper/2206.04355/) (2022)
- [FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning](https://mlsanity.com/paper/2104.14210/) (2021)
- [Node Dependent Local Smoothing for Scalable Graph Learning](https://mlsanity.com/paper/2110.14377/) (2021)
- [Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs](https://mlsanity.com/paper/2212.09034/) (2022)
- [PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm](https://mlsanity.com/paper/2203.00638/) (2022)
- [Model Degradation Hinders Deep Graph Neural Networks](https://mlsanity.com/paper/2206.04361/) (2022)
- [Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching](https://mlsanity.com/paper/2312.16560/) (2023)
- [Evaluating Deep Graph Neural Networks](https://mlsanity.com/paper/2108.00955/) (2021)
- [ROD: Reception-aware Online Distillation for Sparse Graphs](https://mlsanity.com/paper/2107.11789/) (2021)
- [GraphHop: An Enhanced Label Propagation Method for Node Classification](https://mlsanity.com/paper/2101.02326/) (2021)
- [A Meta-Learning Approach for Training Explainable Graph Neural Networks](https://mlsanity.com/paper/2109.09426/) (2021)
- [Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering](https://mlsanity.com/paper/2107.04755/) (2021)
- [Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach](https://mlsanity.com/paper/2506.13083/) (2025)
- [FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection](https://mlsanity.com/paper/2508.10594/) (2025)
- [Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction](https://mlsanity.com/paper/2111.15119/) (2021)
- [Adversarial Graph Disentanglement](https://mlsanity.com/paper/2103.07295/) (2021)
- [GMLP: Building Scalable and Flexible Graph Neural Networks with Feature-Message Passing](https://mlsanity.com/paper/2104.09880/) (2021)
- [Graph Attention MLP with Reliable Label Utilization](https://mlsanity.com/paper/2108.10097/) (2021)
- [EGRC-Net: Embedding-induced Graph Refinement Clustering Network](https://mlsanity.com/paper/2211.10627/) (2022)
- [Steering Graph Neural Networks with Pinning Control](https://mlsanity.com/paper/2303.01265/) (2023)
- [How Graph Neural Networks Learn: Lessons from Training Dynamics](https://mlsanity.com/paper/2310.05105/) (2023)
- [ADMP-GNN: Adaptive Depth Message Passing GNN](https://mlsanity.com/paper/2509.01170/) (2025)
- [Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text](https://mlsanity.com/paper/2301.02983/) (2023)
- [Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks](https://mlsanity.com/paper/2302.11479/) (2023)
- [EWasteNet: A Two-Stream Data Efficient Image Transformer Approach for E-Waste Classification](https://mlsanity.com/paper/2311.12823/) (2023)
- [Unifews: You Need Fewer Operations for Efficient Graph Neural Networks](https://mlsanity.com/paper/2403.13268/) (2024)
- [Early-Exit Graph Neural Networks](https://mlsanity.com/paper/2505.18088/) (2025)
- [TeKo: Text-Rich Graph Neural Networks with External Knowledge](https://mlsanity.com/paper/2206.07253/) (2022)
- [DFG-NAS: Deep and Flexible Graph Neural Architecture Search](https://mlsanity.com/paper/2206.08582/) (2022)
- [GEN: A Practical Alternative to Graph Transformers for Long-Range Graph Modeling](https://mlsanity.com/paper/2401.01233/) (2024)

## Abstract (arXiv)

Graph convolutional networks (GCNs) are a family of neural network models that perform inference on graph data by interleaving vertex-wise operations and message-passing exchanges across nodes. Concerning the latter, two key questions arise: (i) how to design a differentiable exchange protocol (e.g., a 1-hop Laplacian smoothing in the original GCN), and (ii) how to characterize the trade-off in complexity with respect to the local updates. In this paper, we show that state-of-the-art results can be achieved by adapting the number of communication steps independently at every node. In particular, we endow each node with a halting unit (inspired by Graves' adaptive computation time) that after every exchange decides whether to continue communicating or not. We show that the proposed adaptive propagation GCN (AP-GCN) achieves superior or similar results to the best proposed models so far on a number of benchmarks, while requiring a small overhead in terms of additional parameters. We also investigate a regularization term to enforce an explicit trade-off between communication and accuracy. The code for the AP-GCN experiments is released as an open-source library.