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 RandomWalk Networks(PRWN), built on top of Prototypical Networks (PN). We develop a random walk semisupervised 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.
Original language | English (US) |
---|---|
Pages | 45-57 |
Number of pages | 13 |
State | Published - 2021 |
Event | 2021 AAAI Workshop on Meta-Learning and MetaDL Challenge - Virtual, Online Duration: Feb 9 2021 → … |
Conference
Conference | 2021 AAAI Workshop on Meta-Learning and MetaDL Challenge |
---|---|
City | Virtual, Online |
Period | 02/9/21 → … |
ASJC Scopus subject areas
- Artificial Intelligence
- Software
- Control and Systems Engineering
- Statistics and Probability