Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately

7 December 2020

Papers citing "Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately"

22 / 22 papers shown

Title
InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models Yiming Li Xiaogeng Liu SILM 42 5 0 30 Oct 2024
LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views Yuji Roh Qingyun Liu Huan Gui Zhe Yuan Yujin Tang ... Liang Liu Shuchao Bi Lichan Hong Ed H. Chi Zhe Zhao 46 1 0 07 Feb 2024
Spurious Correlations and Where to Find Them Gautam Sreekumar Vishnu Naresh Boddeti CML 22 3 0 21 Aug 2023
Collaborative Development of NLP models Fereshte Khani Marco Tulio Ribeiro 38 2 0 20 May 2023
Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks Lorenz Linhardt Klaus-Robert Muller G. Montavon AAML 29 7 0 12 Apr 2023
Task Discovery: Finding the Tasks that Neural Networks Generalize on Andrei Atanov Andrei Filatov Teresa Yeo Ajay Sohmshetty Amir Zamir OOD 45 10 0 01 Dec 2022
Unveiling the Tapestry: the Interplay of Generalization and Forgetting in Continual Learning Zenglin Shi Jing Jie Ying Sun J. Lim Mengmi Zhang CLL 42 1 0 21 Nov 2022
MaskTune: Mitigating Spurious Correlations by Forcing to Explore Saeid Asgari Taghanaki Aliasghar Khani Fereshte Khani A. Gholami Linh-Tam Tran Ali Mahdavi-Amiri Ghassan Hamarneh AAML 41 45 0 30 Sep 2022
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift Ananya Kumar Tengyu Ma Percy Liang Aditi Raghunathan UQCV OODD OOD 45 38 0 18 Jul 2022
Learning to Increase the Power of Conditional Randomization Tests Shalev Shaer Yaniv Romano CML 31 2 0 03 Jul 2022
Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection Indira Sen Mattia Samory Claudia Wagner Isabelle Augenstein 26 17 0 09 May 2022
Understanding Rare Spurious Correlations in Neural Networks Yao-Yuan Yang Chi-Ning Chou Kamalika Chaudhuri AAML 18 25 0 10 Feb 2022
Conditional entropy minimization principle for learning domain invariant representation features Thuan Q. Nguyen Boyang Lyu Prakash Ishwar matthias. scheutz Shuchin Aeron OOD 32 7 0 25 Jan 2022
The Effect of Model Size on Worst-Group Generalization Alan Pham Eunice Chan V. Srivatsa Dhruba Ghosh Yaoqing Yang Yaodong Yu Ruiqi Zhong Joseph E. Gonzalez Jacob Steinhardt 23 5 0 08 Dec 2021
Human Imperceptible Attacks and Applications to Improve Fairness Xinru Hua Huanzhong Xu Jose H. Blanchet V. Nguyen AAML 27 3 0 30 Nov 2021
Sample Selection for Fair and Robust Training Yuji Roh Kangwook Lee Steven Euijong Whang Changho Suh 21 61 0 27 Oct 2021
Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models Tianlu Wang Rohit Sridhar Diyi Yang Xuezhi Wang AAML 120 72 0 14 Oct 2021
On the Importance of Regularisation & Auxiliary Information in OOD Detection John Mitros Brian Mac Namee 21 2 0 15 Jul 2021
Can Subnetwork Structure be the Key to Out-of-Distribution Generalization? Dinghuai Zhang Kartik Ahuja Yilun Xu Yisen Wang Aaron Courville OOD 20 95 0 05 Jun 2021
An Empirical Framework for Domain Generalization in Clinical Settings Haoran Zhang Natalie Dullerud Laleh Seyyed-Kalantari Q. Morris Shalmali Joshi Marzyeh Ghassemi OOD AI4CE 26 59 0 20 Mar 2021
Understanding and Mitigating Accuracy Disparity in Regression Jianfeng Chi Yuan Tian Geoffrey J. Gordon Han Zhao 27 25 0 24 Feb 2021
Learning Adversarially Fair and Transferable Representations David Madras Elliot Creager T. Pitassi R. Zemel FaML 233 674 0 17 Feb 2018