Learning with Group Noise
This addresses a practical challenge in machine learning for applications with group-level noise, but it appears incremental as it builds on existing noisy learning approaches.
The paper tackles the problem of learning with group noise, where coarse-grained accurate relations are obscured by fine-grained uncertainty, by proposing a Max-Matching method that selects the most confident object in each group to drop noise. The method demonstrates effectiveness on real-world datasets across several learning paradigms, though no concrete numbers are provided.
Machine learning in the context of noise is a challenging but practical setting to plenty of real-world applications. Most of the previous approaches in this area focus on the pairwise relation (casual or correlational relationship) with noise, such as learning with noisy labels. However, the group noise, which is parasitic on the coarse-grained accurate relation with the fine-grained uncertainty, is also universal and has not been well investigated. The challenge under this setting is how to discover true pairwise connections concealed by the group relation with its fine-grained noise. To overcome this issue, we propose a novel Max-Matching method for learning with group noise. Specifically, it utilizes a matching mechanism to evaluate the relation confidence of each object w.r.t. the target, meanwhile considering the Non-IID characteristics among objects in the group. Only the most confident object is considered to learn the model, so that the fine-grained noise is mostly dropped. The performance on arange of real-world datasets in the area of several learning paradigms demonstrates the effectiveness of Max-Matching