# Learning to Propagate for Graph Meta-Learning

arXiv: https://arxiv.org/abs/1909.05024 · HTML: https://mlsanity.com/paper/1909.05024/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2019.

## Built on by (most cited first, 29 of 29)

- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [Free Lunch for Few-shot Learning: Distribution Calibration](https://mlsanity.com/paper/2101.06395/) (2021)
- [Federated Learning from Pre-Trained Models: A Contrastive Learning Approach](https://mlsanity.com/paper/2209.10083/) (2022)
- [Task-Adaptive Few-shot Node Classification](https://mlsanity.com/paper/2206.11972/) (2022)
- [Graph Few-shot Learning with Task-specific Structures](https://mlsanity.com/paper/2210.12130/) (2022)
- [Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification](https://mlsanity.com/paper/2212.05606/) (2022)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [Learning to Learn from APIs: Black-Box Data-Free Meta-Learning](https://mlsanity.com/paper/2305.18413/) (2023)
- [Meta-Inductive Node Classification across Graphs](https://mlsanity.com/paper/2105.06725/) (2021)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [Relational Multi-Task Learning: Modeling Relations between Data and Tasks](https://mlsanity.com/paper/2303.07666/) (2023)
- [Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation](https://mlsanity.com/paper/2207.06989/) (2022)
- [Few-shot Node Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2301.02708/) (2023)
- [Automated Deep Learning: Neural Architecture Search Is Not the End](https://mlsanity.com/paper/2112.09245/) (2021)
- [Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?](https://mlsanity.com/paper/2203.03059/) (2022)
- [ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning](https://mlsanity.com/paper/2106.08523/) (2021)
- [Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning](https://mlsanity.com/paper/2303.11183/) (2023)
- [Federated Few-shot Learning](https://mlsanity.com/paper/2306.10234/) (2023)
- [Task-Equivariant Graph Few-shot Learning](https://mlsanity.com/paper/2305.18758/) (2023)
- [Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning](https://mlsanity.com/paper/2103.00771/) (2021)
- [Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approach](https://mlsanity.com/paper/2201.03326/) (2022)
- [Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach](https://mlsanity.com/paper/2310.18918/) (2023)
- [Dual-level Mixup for Graph Few-shot Learning with Fewer Tasks](https://mlsanity.com/paper/2502.14158/) (2025)
- [Combat Data Shift in Few-shot Learning with Knowledge Graph](https://mlsanity.com/paper/2101.11354/) (2021)
- [Model-Agnostic Graph Regularization for Few-Shot Learning](https://mlsanity.com/paper/2102.07077/) (2021)
- [Episodic memory governs choices: An RNN-based reinforcement learning model for decision-making task](https://mlsanity.com/paper/2103.03679/) (2021)
- [Robust Graph Meta-learning for Weakly-supervised Few-shot Node Classification](https://mlsanity.com/paper/2106.06873/) (2021)
- [Fair Few-shot Learning with Auxiliary Sets](https://mlsanity.com/paper/2308.14338/) (2023)
- [CPT: Competence-progressive Training Strategy for Few-shot Node Classification](https://mlsanity.com/paper/2402.00450/) (2024)

## Abstract (arXiv)

Meta-learning extracts common knowledge from learning different tasks and uses it for unseen tasks. It can significantly improve tasks that suffer from insufficient training data, e.g., few shot learning. In most meta-learning methods, tasks are implicitly related by sharing parameters or optimizer. In this paper, we show that a meta-learner that explicitly relates tasks on a graph describing the relations of their output dimensions (e.g., classes) can significantly improve few shot learning. The graph's structure is usually free or cheap to obtain but has rarely been explored in previous works. We develop a novel meta-learner of this type for prototype-based classification, in which a prototype is generated for each class, such that the nearest neighbor search among the prototypes produces an accurate classification. The meta-learner, called "Gated Propagation Network (GPN)", learns to propagate messages between prototypes of different classes on the graph, so that learning the prototype of each class benefits from the data of other related classes. In GPN, an attention mechanism aggregates messages from neighboring classes of each class, with a gate choosing between the aggregated message and the message from the class itself. We train GPN on a sequence of tasks from many-shot to few shot generated by subgraph sampling. During training, it is able to reuse and update previously achieved prototypes from the memory in a life-long learning cycle. In experiments, under different training-test discrepancy and test task generation settings, GPN outperforms recent meta-learning methods on two benchmark datasets. The code of GPN and dataset generation is available at https://github.com/liulu112601/Gated-Propagation-Net.