Towards trustworthy and aligned machine learning: A data-centric survey with causality perspectives
The trustworthiness of machine learning has emerged as a critical topic in the field,
encompassing various applications and research areas such as robustness, security …
encompassing various applications and research areas such as robustness, security …
Toward learning robust and invariant representations with alignment regularization and data augmentation
Data augmentation has been proven to be an effective technique for developing machine
learning models that are robust to known classes of distributional shifts (eg, rotations of …
learning models that are robust to known classes of distributional shifts (eg, rotations of …
Squared Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations
Data augmentation is one of the most popular techniques for improving the robustness of
neural networks. In addition to directly training the model with original samples and …
neural networks. In addition to directly training the model with original samples and …
[PDF][PDF] Toward Robust Machine Learning by Countering Superficial Features
H Wang - 2021 - kilthub.cmu.edu
Abstract Machine learning, especially deep neural networks, has demonstrated remarkable
empirical performances over various benchmarks. A potential next step is to extend these …
empirical performances over various benchmarks. A potential next step is to extend these …
On the Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations
H Wang, Z Huang, X Wu, E Xing - openreview.net
Data augmentation is one of the most popular techniques for improving the robustness of
neural networks. In addition to directly training the model with original samples and …
neural networks. In addition to directly training the model with original samples and …