Papers › Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning

Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning

25 May 2018ICLR 2019 5arXiv:1805.10002archive 2025-07-28

Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang, Yi Yang

The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class. The recently introduced meta-learning approaches tackle this problem by learning a generic classifier across a large number of multiclass classification tasks and generalizing the model to a new task. Yet, even with such meta-learning, the low-data problem in the novel classification task still remains. In this paper, we propose Transductive Propagation Network (TPN), a novel meta-learning framework for transductive inference that classifies the entire test set at once to alleviate the low-data problem. Specifically, we propose to learn to propagate labels from labeled instances to unlabeled test instances, by learning a graph construction module that exploits the manifold structure in the data. TPN jointly learns both the parameters of feature embedding and the graph construction in an end-to-end manner. We validate TPN on multiple benchmark datasets, on which it largely outperforms existing few-shot learning approaches and achieves the state-of-the-art results.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

csyanbin/TPN-pytorch officialpytorchSyntology: not harvested report
csyanbin/TPN tfSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot Image ClassificationFew-Shot LearningGeneral ClassificationMeta-Learninggraph construction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification Mini-Imagenet 10-way (1-shot) TPN (Higher Shot) Accuracy 38.4 #5 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (1-shot) Label Propagation Accuracy 35.2 #7 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (5-shot) TPN (Higher Shot) Accuracy 52.8 #6 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (5-shot) Label Propagation Accuracy 51.2 #7 of 14 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (1-shot) TPN (Higher Shot) Accuracy 44.8 #5 of 13 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (1-shot) Label Propagation Accuracy 39.4 #6 of 13 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (5-shot) TPN (Higher Shot) Accuracy 59.4 #5 of 13 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (5-shot) Label Propagation Accuracy 57.9 #8 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Transductive Inference

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections