# CPT: Competence-progressive Training Strategy for Few-shot Node Classification

arXiv: https://arxiv.org/abs/2402.00450 · HTML: https://mlsanity.com/paper/2402.00450/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 53 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Builds on (most cited first, 29 of 29)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [Meta-Transfer Learning for Few-Shot Learning](https://mlsanity.com/paper/1812.02391/) (2018)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Competence-based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/1903.09848/) (2019)
- [Meta-GNN: On Few-shot Node Classification in Graph Meta-learning](https://mlsanity.com/paper/1905.09718/) (2019)
- [Inferring Networks of Substitutable and Complementary Products](https://mlsanity.com/paper/1506.08839/) (2015)
- [Graph Prototypical Networks for Few-shot Learning on Attributed Networks](https://mlsanity.com/paper/2006.12739/) (2020)
- [Graph Meta Learning via Local Subgraphs](https://mlsanity.com/paper/2006.07889/) (2020)
- [Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks](https://mlsanity.com/paper/2004.13826/) (2020)
- [Task-Adaptive Few-shot Node Classification](https://mlsanity.com/paper/2206.11972/) (2022)
- [Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understanding](https://mlsanity.com/paper/1901.01415/) (2019)
- [Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1911.08717/) (2019)
- [Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures](https://mlsanity.com/paper/2002.12815/) (2020)
- [Learning to Propagate for Graph Meta-Learning](https://mlsanity.com/paper/1909.05024/) (2019)
- [Adaptive Task Sampling for Meta-Learning](https://mlsanity.com/paper/2007.08735/) (2020)
- [CLNode: Curriculum Learning for Node Classification](https://mlsanity.com/paper/2206.07258/) (2022)
- [Curriculum Graph Machine Learning: A Survey](https://mlsanity.com/paper/2302.02926/) (2023)
- [Relation-aware Heterogeneous Graph for User Profiling](https://mlsanity.com/paper/2110.07181/) (2021)
- [Generic and Trend-aware Curriculum Learning for Relation Extraction in Graph Neural Networks](https://mlsanity.com/paper/2205.08625/) (2022)
- [Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-N Recommendation](https://mlsanity.com/paper/2106.06722/) (2021)
- [Curriculum Learning for Graph Neural Networks: A Multiview Competence-based Approach](https://mlsanity.com/paper/2307.08859/) (2023)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have made significant advancements in node classification, but their success relies on sufficient labeled nodes per class in the training data. Real-world graph data often exhibits a long-tail distribution with sparse labels, emphasizing the importance of GNNs' ability in few-shot node classification, which entails categorizing nodes with limited data. Traditional episodic meta-learning approaches have shown promise in this domain, but they face an inherent limitation: it might lead the model to converge to suboptimal solutions because of random and uniform task assignment, ignoring task difficulty levels. This could lead the meta-learner to face complex tasks too soon, hindering proper learning. Ideally, the meta-learner should start with simple concepts and advance to more complex ones, like human learning. So, we introduce CPT, a novel two-stage curriculum learning method that aligns task difficulty with the meta-learner's progressive competence, enhancing overall performance. Specifically, in CPT's initial stage, the focus is on simpler tasks, fostering foundational skills for engaging with complex tasks later. Importantly, the second stage dynamically adjusts task difficulty based on the meta-learner's growing competence, aiming for optimal knowledge acquisition. Extensive experiments on popular node classification datasets demonstrate significant improvements of our strategy over existing methods.