# Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First

arXiv: https://arxiv.org/abs/2310.18735 · HTML: https://mlsanity.com/paper/2310.18735/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 56 references that are in the map.
- First posted on arXiv 28 Oct 2023.

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

- [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)
- [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)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](https://mlsanity.com/paper/1905.00067/) (2019)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings](https://mlsanity.com/paper/2006.13009/) (2020)
- [Learning to Drop: Robust Graph Neural Network via Topological Denoising](https://mlsanity.com/paper/2011.07057/) (2020)
- [Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks](https://mlsanity.com/paper/1802.03796/) (2018)
- [A Comprehensive Survey on Deep Graph Representation Learning](https://mlsanity.com/paper/2304.05055/) (2023)
- [Deep Graph Representation Learning and Optimization for Influence Maximization](https://mlsanity.com/paper/2305.02200/) (2023)
- [CLNode: Curriculum Learning for Node Classification](https://mlsanity.com/paper/2206.07258/) (2022)
- [ADMM for Efficient Deep Learning with Global Convergence](https://mlsanity.com/paper/1905.13611/) (2019)
- [Deep Generative Model for Periodic Graphs](https://mlsanity.com/paper/2201.11932/) (2022)
- [Graph Neural Network with Curriculum Learning for Imbalanced Node Classification](https://mlsanity.com/paper/2202.02529/) (2022)
- [Source Localization of Graph Diffusion via Variational Autoencoders for Graph Inverse Problems](https://mlsanity.com/paper/2206.12327/) (2022)
- [Curriculum Graph Machine Learning: A Survey](https://mlsanity.com/paper/2302.02926/) (2023)

## Built on by (most cited first, 10 of 10)

- [Uncertainty-aware Evidential Fusion-based Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2404.06177/) (2024)
- [GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks](https://mlsanity.com/paper/2510.22451/) (2025)
- [Curriculum Guided Personalized Subgraph Federated Learning](https://mlsanity.com/paper/2509.00402/) (2025)
- [Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning](https://mlsanity.com/paper/2410.12096/) (2024)
- [Representation Learning of Geometric Trees](https://mlsanity.com/paper/2408.08799/) (2024)
- [Non-Euclidean Spatial Graph Neural Network](https://mlsanity.com/paper/2312.10808/) (2023)
- [SpanGNN: Towards Memory-Efficient Graph Neural Networks via Spanning Subgraph Training](https://mlsanity.com/paper/2406.04938/) (2024)
- [Iterative Misclassification Error Training (IMET): An Optimized Neural Network Training Technique for Image Classification](https://mlsanity.com/paper/2507.02979/) (2025)
- [Bandit Guided Submodular Curriculum for Adaptive Subset Selection](https://mlsanity.com/paper/2511.22944/) (2025)
- [CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion](https://mlsanity.com/paper/2609.08244/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved great success in representing data with dependencies by recursively propagating and aggregating messages along the edges. However, edges in real-world graphs often have varying degrees of difficulty, and some edges may even be noisy to the downstream tasks. Therefore, existing GNNs may lead to suboptimal learned representations because they usually treat every edge in the graph equally. On the other hand, Curriculum Learning (CL), which mimics the human learning principle of learning data samples in a meaningful order, has been shown to be effective in improving the generalization ability and robustness of representation learners by gradually proceeding from easy to more difficult samples during training. Unfortunately, existing CL strategies are designed for independent data samples and cannot trivially generalize to handle data dependencies. To address these issues, we propose a novel CL strategy to gradually incorporate more edges into training according to their difficulty from easy to hard, where the degree of difficulty is measured by how well the edges are expected given the model training status. We demonstrate the strength of our proposed method in improving the generalization ability and robustness of learned representations through extensive experiments on nine synthetic datasets and nine real-world datasets. The code for our proposed method is available at https://github.com/rollingstonezz/Curriculum_learning_for_GNNs.