GM-PLL: Graph Matching based Partial Label Learning
This work addresses the challenge of disambiguating candidate labels in machine learning, which is important for applications with noisy or incomplete labeling, but it appears incremental as it builds on existing graph matching techniques.
The paper tackles the problem of Partial Label Learning (PLL), where each training example has multiple candidate labels with only one correct, by reformulating it as a matching selection problem and proposing a Graph Matching based framework (GM-PLL) that extends traditional one-to-one matching to many-to-one constraints. The method achieves superior or comparable performance to state-of-the-art methods in experiments on artificial and real-world datasets.
Partial Label Learning (PLL) aims to learn from the data where each training example is associated with a set of candidate labels, among which only one is correct. The key to deal with such problem is to disambiguate the candidate label sets and obtain the correct assignments between instances and their candidate labels. In this paper, we interpret such assignments as instance-to-label matchings, and reformulate the task of PLL as a matching selection problem. To model such problem, we propose a novel Graph Matching based Partial Label Learning (GM-PLL) framework, where Graph Matching (GM) scheme is incorporated owing to its excellent capability of exploiting the instance and label relationship. Meanwhile, since conventional one-to-one GM algorithm does not satisfy the constraint of PLL problem that multiple instances may correspond to the same label, we extend a traditional one-to-one probabilistic matching algorithm to the many-to-one constraint, and make the proposed framework accommodate to the PLL problem. Moreover, we also propose a relaxed matching prediction model, which can improve the prediction accuracy via GM strategy. Extensive experiments on both artificial and real-world data sets demonstrate that the proposed method can achieve superior or comparable performance against the state-of-the-art methods.