---
title: "Few-Shot Partial-Label Learning"
authors:
  - "Yunfeng Zhao"
  - "Guoxian Yu"
  - "Lei Liu"
  - "Zhongmin Yan"
  - "Lizhen Cui"
  - "Carlotta Domeniconi"
doi: "10.24963/ijcai.2021/475"
url: "https://ijcai.org/proceedings/2021/475"
pdf: "https://ijcai.org/proceedings/2021/0475.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "3448-3454"
track: "Main Track"
keywords:
  - "Machine Learning: Weakly Supervised Learning"
  - "Machine Learning: Multi-instance; Multi-label; Multi-view learning"
  - "Machine Learning: Transfer, Adaptation, Multi-task Learning"
---

# Few-Shot Partial-Label Learning

Yunfeng Zhao, Guoxian Yu, Lei Liu, Zhongmin Yan, Lizhen Cui, Carlotta Domeniconi

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 3448-3454. DOI: [10.24963/ijcai.2021/475](https://doi.org/10.24963/ijcai.2021/475)

## Abstract

Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label. A basic promise of existing PLL solutions is that there are sufficient partial-label (PL) samples for training. However, it is more common than not to have just few PL samples at hand when dealing with new tasks. Furthermore, existing few-shot learning algorithms assume precise labels of the support set; as such,  irrelevant labels may seriously mislead the meta-learner  and thus lead to a compromised performance. How to enable PLL under a few-shot learning setting is an important problem, but not yet well studied. In this paper, we introduce an approach called FsPLL (Few-shot PLL).  FsPLL first performs adaptive distance metric learning by an embedding network and rectifying prototypes on the tasks previously encountered. Next, it calculates the prototype of each class of a new task in the embedding network. An unseen example can then be classified via its distance to each prototype. Experimental results on widely-used few-shot datasets demonstrate that our FsPLL can achieve a superior performance than the state-of-the-art methods, and it needs fewer samples for quickly adapting to new tasks.