NoiseRank: Unsupervised Label Noise Reduction with Dependence Models
This addresses label noise reduction for machine learning applications without requiring supervision, making it scalable and broadly applicable across domains.
The paper tackles the problem of label noise in datasets by proposing NoiseRank, an unsupervised method using Markov Random Fields to estimate and rank incorrectly labeled instances, which improves state-of-the-art classification on Food101-N with ~20% noise and is effective on Clothing-1M with ~40% noise.
Label noise is increasingly prevalent in datasets acquired from noisy channels. Existing approaches that detect and remove label noise generally rely on some form of supervision, which is not scalable and error-prone. In this paper, we propose NoiseRank, for unsupervised label noise reduction using Markov Random Fields (MRF). We construct a dependence model to estimate the posterior probability of an instance being incorrectly labeled given the dataset, and rank instances based on their estimated probabilities. Our method 1) Does not require supervision from ground-truth labels, or priors on label or noise distribution. 2) It is interpretable by design, enabling transparency in label noise removal. 3) It is agnostic to classifier architecture/optimization framework and content modality. These advantages enable wide applicability in real noise settings, unlike prior works constrained by one or more conditions. NoiseRank improves state-of-the-art classification on Food101-N (~20% noise), and is effective on high noise Clothing-1M (~40% noise).