Learning to Predict Trustworthiness with Steep Slope LossDownload PDF

Published: 09 Nov 2021, Last Modified: 08 Sept 2024NeurIPS 2021 PosterReaders: Everyone
Keywords: Deep leearning, Classification, Trustworthiness
Abstract: Understanding the trustworthiness of a prediction yielded by a classifier is critical for the safe and effective use of AI models. Prior efforts have been proven to be reliable on small-scale datasets. In this work, we study the problem of predicting trustworthiness on real-world large-scale datasets, where the task is more challenging due to high-dimensional features, diverse visual concepts, and a large number of samples. In such a setting, we observe that the trustworthiness predictors trained with prior-art loss functions, i.e., the cross entropy loss, focal loss, and true class probability confidence loss, are prone to view both correct predictions and incorrect predictions to be trustworthy. The reasons are two-fold. Firstly, correct predictions are generally dominant over incorrect predictions. Secondly, due to the data complexity, it is challenging to differentiate the incorrect predictions from the correct ones on real-world large-scale datasets. To improve the generalizability of trustworthiness predictors, we propose a novel steep slope loss to separate the features w.r.t. correct predictions from the ones w.r.t. incorrect predictions by two slide-like curves that oppose each other. The proposed loss is evaluated with two representative deep learning models, i.e., Vision Transformer and ResNet, as trustworthiness predictors. We conduct comprehensive experiments and analyses on ImageNet, which show that the proposed loss effectively improves the generalizability of trustworthiness predictors. The code and pre-trained trustworthiness predictors for reproducibility are available at \url{https://github.com/luoyan407/predict_trustworthiness}.
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
TL;DR: We study the problem of predicting trustworthiness on a real-world large-scale dataset.
Supplementary Material: pdf
Code: https://github.com/luoyan407/predict_trustworthiness
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 5 code implementations](https://www.catalyzex.com/paper/learning-to-predict-trustworthiness-with/code)
17 Replies

Loading