CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks
This work addresses the problem of reliable uncertainty quantification for neural network users, offering a computationally efficient alternative to existing methods, though it appears incremental as it builds on Interval Neural Networks.
The paper tackles uncertainty estimation in neural network classification by proposing Credal-Set Interval Neural Networks (CreINNs), which predict probability bounds for each class to define a credal set, achieving superior or comparable uncertainty estimation to variational BNNs and Deep Ensembles while significantly reducing computational complexity during inference.
Effective uncertainty estimation is becoming increasingly attractive for enhancing the reliability of neural networks. This work presents a novel approach, termed Credal-Set Interval Neural Networks (CreINNs), for classification. CreINNs retain the fundamental structure of traditional Interval Neural Networks, capturing weight uncertainty through deterministic intervals. CreINNs are designed to predict an upper and a lower probability bound for each class, rather than a single probability value. The probability intervals can define a credal set, facilitating estimating different types of uncertainties associated with predictions. Experiments on standard multiclass and binary classification tasks demonstrate that the proposed CreINNs can achieve superior or comparable quality of uncertainty estimation compared to variational Bayesian Neural Networks (BNNs) and Deep Ensembles. Furthermore, CreINNs significantly reduce the computational complexity of variational BNNs during inference. Moreover, the effective uncertainty quantification of CreINNs is also verified when the input data are intervals.