# Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph

arXiv: https://arxiv.org/abs/1905.04042 · HTML: https://mlsanity.com/paper/1905.04042/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2019.

## Built on by (most cited first, 15 of 15)

- [Free Lunch for Few-shot Learning: Distribution Calibration](https://mlsanity.com/paper/2101.06395/) (2021)
- [PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences](https://mlsanity.com/paper/2205.13713/) (2022)
- [Few-shot Network Anomaly Detection via Cross-network Meta-learning](https://mlsanity.com/paper/2102.11165/) (2021)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2106.06326/) (2021)
- [ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback](https://mlsanity.com/paper/2107.14035/) (2021)
- [Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation](https://mlsanity.com/paper/2510.08962/) (2025)
- [Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition](https://mlsanity.com/paper/2101.05018/) (2021)
- [Hierarchical Material Recognition from Local Appearance](https://mlsanity.com/paper/2505.22911/) (2025)
- [Model-Agnostic Graph Regularization for Few-Shot Learning](https://mlsanity.com/paper/2102.07077/) (2021)
- [Fine-grained Classes and How to Find Them](https://mlsanity.com/paper/2406.11070/) (2024)
- [A Survey of Learning on Small Data: Generalization, Optimization, and Challenge](https://mlsanity.com/paper/2207.14443/) (2022)
- [Unifying Label-inputted Graph Neural Networks with Deep Equilibrium Models](https://mlsanity.com/paper/2211.10629/) (2022)
- [Holistic Prototype Attention Network for Few-Shot VOS](https://mlsanity.com/paper/2307.07933/) (2023)
- [Graph Entropy Minimization for Semi-supervised Node Classification](https://mlsanity.com/paper/2305.19502/) (2023)

## Abstract (arXiv)

A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototype propagation network (PPN) trained on few-shot tasks together with data annotated by coarse-label. Given a category graph of the targeted fine-classes and some weakly-labeled coarse-classes, PPN learns an attention mechanism which propagates the prototype of one class to another on the graph, so that the K-nearest neighbor (KNN) classifier defined on the propagated prototypes results in high accuracy across different few-shot tasks. The training tasks are generated by subgraph sampling, and the training objective is obtained by accumulating the level-wise classification loss on the subgraph. The resulting graph of prototypes can be continually re-used and updated for new tasks and classes. We also introduce two practical test/inference settings which differ according to whether the test task can leverage any weakly-supervised information as in training. On two benchmarks, PPN significantly outperforms most recent few-shot learning methods in different settings, even when they are also allowed to train on weakly-labeled data.