# Semi-Supervised Few-Shot Learning with Prototypical Random Walks

Source: [Semi-Supervised Few-Shot Learning with Prototypical Random Walks](<https://www.sota2.com/research/paper/68fa69361e209131cea20d85>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:55:51.498Z

Authors: Ahmed Ayyad, Yuchen Li, Nassir Navab, Shadi Albarqouni, Mohamed Elhoseiny

Published: 2019-03-06T03:54:40.000Z

## Abstract

Recent progress has shown that few-shot learning can be improved with access to unlabelled data, known as semi-supervised few-shot learning(SS-FSL). We introduce an SS-FSL approach, dubbed as Prototypical Random Walk Networks(PRWN), built on top of Prototypical Networks (PN). We develop a random walk semi-supervised loss that enables the network to learn representations that are compact and well-separated. Our work is related to the very recent development of graph-based approaches for few-shot learning. However, we show that compact and well-separated class representations can be achieved by modeling our prototypical random walk notion without needing additional graph-NN parameters or requiring a transductive setting where a collective test set is provided. Our model outperforms baselines in most benchmarks with significant improvements in some cases. Our model, trained with 40$\\%$ of the data as labeled, compares competitively against fully supervised prototypical networks, trained on 100$\\%$ of the labels, even outperforming it in the 1-shot mini-Imagenet case with 50.89$\\%$ to 49.4$\\%$ accuracy. We also show that our loss is resistant to distractors, unlabeled data that does not belong to any of the training classes, and hence reflecting robustness to labeled/unlabeled class distribution mismatch. Associated GitHub page can be found at https://prototypical-random-walk.github.io.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1903.02164>)

[PDF](<https://arxiv.org/pdf/1903.02164.pdf>)
