.png){kind=icon}
返回
Distributionally Robust Learning With Stable Adversarial Training
.png){kind=icon}
OA
AI
DOI：10.1109/TKDE.2022.3224056.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. There is an emerging literature on tackling this problem by minimizing the worst-case risk over an uncertainty set. However, existing methods mostly construct ambiguity sets by treating all variables equally regardless of the stability of their correlations with the target, resulting in the overwhelmingly-large uncertainty set and low confidence of the learner. In this paper, we propose a novel Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set and conduct differentiated robustness optimization, where covariates are differentiated according to the stability of their correlations with the target. We theoretically show that our method is tractable for stochastic gradient-based optimization and provide the performance guarantees for our method. Empirical studies on both simulation and real datasets validate the effectiveness of our method in terms of uniformly good performance across unknown distributional shifts.
Keyword:
Stable adversarial learning
spurious correlation
distributionally robust learning
wasserstein distance
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
3-O-Sulfated Heparan Sulfate Recognized by the Antibody HS4C3 Contribute to the Differentiation of Mouse Embryonic Stem Cells via Fas Signaling.png)
PLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏Detection of feigned recognition memory impairment using the old/new effect of the event-related potential使用事件相关电位的新旧效应检测假装识别记忆障碍
PREAI
分享收藏Stable learning establishes some common ground between causal inference and machine learning稳定学习在因果推理和机器学习之间建立了一些共同点
PREAI
分享收藏分享收藏分享收藏
查看更多内容