# Enhancing Imbalanced Node Classification via Curriculum-Guided Feature Learning and Three-Stage Attention Network

arXiv: https://arxiv.org/abs/2602.03808 · HTML: https://mlsanity.com/paper/2602.03808/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [Multi-View Graph Convolutional Network for Multimedia Recommendation](https://mlsanity.com/paper/2308.03588/) (2023)
- [LTE4G: Long-Tail Experts for Graph Neural Networks](https://mlsanity.com/paper/2208.10205/) (2022)
- [High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing](https://mlsanity.com/paper/2201.06848/) (2022)
- [GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification](https://mlsanity.com/paper/2302.12814/) (2023)
- [Class Imbalance Problem in Data Mining Review](https://mlsanity.com/paper/1305.1707/) (2013)
- [A Meta-Learning Approach for Training Explainable Graph Neural Networks](https://mlsanity.com/paper/2109.09426/) (2021)
- [Explainable Spatio-Temporal Graph Neural Networks](https://mlsanity.com/paper/2310.17149/) (2023)
- [Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition](https://mlsanity.com/paper/2310.18765/) (2023)
- [Graph Ordering Attention Networks](https://mlsanity.com/paper/2204.05351/) (2022)
- [Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2206.05335/) (2022)
- [Tackling the Imbalance for GNNs](https://mlsanity.com/paper/2110.08690/) (2021)

## Abstract (arXiv)

Imbalanced node classification in graph neural networks (GNNs) happens when some labels are much more common than others, which causes the model to learn unfairly and perform badly on the less common classes. To solve this problem, we propose a Curriculum-Guided Feature Learning and Three-Stage Attention Network (CL3AN-GNN), a learning network that uses a three-step attention system (Engage, Enact, Embed) similar to how humans learn. The model begins by engaging with structurally simpler features, defined as (1) local neighbourhood patterns (1-hop), (2) low-degree node attributes, and (3) class-separable node pairs identified via initial graph convolutional networks and graph attention networks (GCN and GAT) embeddings. This foundation enables stable early learning despite label skew. The Enact stage then addresses complicated aspects: (1) connections that require multiple steps, (2) edges that connect different types of nodes, and (3) nodes at the edges of minority classes by using adjustable attention weights. Finally, Embed consolidates these features via iterative message passing and curriculum-aligned loss weighting. We evaluate CL3AN-GNN on eight Open Graph Benchmark datasets spanning social, biological, and citation networks. Experiments show consistent improvements across all datasets in accuracy, F1-score, and AUC over recent state-of-the-art methods. The model's step-by-step method works well with different types of graph datasets, showing quicker results than training everything at once, better performance on new, imbalanced graphs, and clear explanations of each step using gradient stability and attention correlation learning curves. This work provides both a theoretically grounded framework for curriculum learning in GNNs and practical evidence of its effectiveness against imbalances, validated through metrics, convergence speeds, and generalisation tests.