Sjoerd de Vries

Sjoerd de Vries, Dirk Thierens

In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into account. We investigate whether incorporating label uncertainty, represented as discrete probability distributions over the class labels -- known as soft labels -- improves the predictive performance of classification models. We first demonstrate the potential value of soft label learning (SLL) for estimating model parameters in a simulation experiment, particularly for limited sample sizes and imbalanced data. Subsequently, we compare the performance of various wrapper methods for learning from both hard and soft labels using identical base classifiers. On real-world-inspired synthetic data with clean labels, the SLL methods consistently outperform hard label methods. Since real-world data is often noisy and precise soft labels are challenging to obtain, we study the effect that noisy probability estimates have on model performance. Alongside conventional noise models, our study examines four types of miscalibration that are known to affect human annotators. The results show that SLL methods outperform the hard label methods in the majority of settings. Finally, we evaluate the methods on a real-world dataset with confidence scores, where the SLL methods are shown to match the traditional methods for predicting the (noisy) hard labels while providing more accurate confidence estimates.

Sjoerd de Vries, Dirk Thierens

In many real-world classification tasks, label noise is an unavoidable issue that adversely affects the generalization error of machine learning models. Additionally, evaluating how methods handle such noise is complicated, as the effect label noise has on their performance cannot be accurately quantified without clean labels. Existing research on label noise typically relies on either noisy or oversimplified simulated data as a baseline, into which additional noise with known properties is injected. In this paper, we introduce SYNLABEL, a framework designed to address these limitations by creating noiseless datasets informed by real-world data. SYNLABEL supports defining a pre-specified or learned function as the ground truth function, which can then be used for generating new clean labels. Furthermore, by repeatedly resampling values for selected features within the domain of the function, evaluating the function and aggregating the resulting labels, each data point can be assigned a soft label or label distribution. These distributions capture the inherent uncertainty present in many real-world datasets and enable the direct injection and quantification of label noise. The generated datasets serve as a clean baseline of adjustable complexity, into which various types of noise can be introduced. Additionally, they facilitate research into soft label learning and related applications. We demonstrate the application of SYNLABEL, showcasing its ability to precisely quantify label noise and its improvement over existing methodologies.