Influence Functions in Deep Learning Are Fragile

25 June 2020

Papers citing "Influence Functions in Deep Learning Are Fragile"

50 / 154 papers shown

Title
LESS: Selecting Influential Data for Targeted Instruction Tuning Mengzhou Xia Sadhika Malladi Suchin Gururangan Sanjeev Arora Danqi Chen 80 185 0 06 Feb 2024
Unlearning Traces the Influential Training Data of Language Models Masaru Isonuma Ivan Titov MU 24 6 0 26 Jan 2024
Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation Tong Xie Haoyu Li Andrew Bai Cho-Jui Hsieh TDI 28 2 0 17 Jan 2024
Machine unlearning through fine-grained model parameters perturbation Zhiwei Zuo Zhuo Tang KenLi Li Anwitaman Datta AAML MU 19 0 0 09 Jan 2024
Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective Haoyi Xiong Xuhong Li Xiaofei Zhang Jiamin Chen Xinhao Sun Yuchen Li Zeyi Sun Mengnan Du XAI 35 8 0 09 Jan 2024
In-Database Data Imputation Massimo Perini Milos Nikolic SyDa 28 2 0 07 Jan 2024
Deeper Understanding of Black-box Predictions via Generalized Influence Functions Hyeonsu Lyu Jonggyu Jang Sehyun Ryu H. Yang TDI AI4CE 18 5 0 09 Dec 2023
Adaptive Instrument Design for Indirect Experiments Yash Chandak Shiv Shankar Vasilis Syrgkanis Emma Brunskill 40 4 0 05 Dec 2023
Deployment of a Robust and Explainable Mortality Prediction Model: The COVID-19 Pandemic and Beyond Jacob R. Epifano Stephen Glass Ravichandran Ramachandran Sharad Patel A. Masino Ghulam Rasool 18 0 0 28 Nov 2023
Unifying Corroborative and Contributive Attributions in Large Language Models Theodora Worledge Judy Hanwen Shen Nicole Meister Caleb Winston Carlos Guestrin TDI 24 10 0 20 Nov 2023
SoK: Memorisation in machine learning Dmitrii Usynin Moritz Knolle Georgios Kaissis 17 1 0 06 Nov 2023
A Simple and Efficient Baseline for Data Attribution on Images Vasu Singla Pedro Sandoval-Segura Micah Goldblum Jonas Geiping Tom Goldstein FAtt 28 3 0 03 Nov 2023
Intriguing Properties of Data Attribution on Diffusion Models Xiaosen Zheng Tianyu Pang Chao Du Jing Jiang Min-Bin Lin TDI 34 20 1 01 Nov 2023
Exploring Practitioner Perspectives On Training Data Attribution Explanations Elisa Nguyen Evgenii Kortukov Jean Y. Song Seong Joon Oh TDI 379 1 0 31 Oct 2023
The Memory Perturbation Equation: Understanding Model's Sensitivity to Data Peter Nickl Lu Xu Dharmesh Tailor Thomas Möllenhoff Mohammad Emtiyaz Khan 24 10 0 30 Oct 2023
Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning Zheyuan Liu Guangyao Dou Yijun Tian Chunhui Zhang Eli Chien Ziwei Zhu MU 26 16 0 28 Oct 2023
Sample based Explanations via Generalized Representers Che-Ping Tsai Chih-Kuan Yeh Pradeep Ravikumar FAtt 39 8 0 27 Oct 2023
Fast Model Debias with Machine Unlearning Ruizhe Chen Jianfei Yang Huimin Xiong Jianhong Bai Tianxiang Hu Jinxiang Hao Yang Feng Joey Tianyi Zhou Jian Wu Zuo-Qiang Liu MU 29 57 0 19 Oct 2023
Farzi Data: Autoregressive Data Distillation Noveen Sachdeva Zexue He Wang-Cheng Kang Jianmo Ni D. Cheng Julian McAuley DD 19 3 0 15 Oct 2023
Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning Yihua Zhang Yimeng Zhang Aochuan Chen Jinghan Jia Jiancheng Liu Gaowen Liu Min-Fong Hong Shiyu Chang Sijia Liu AAML 29 8 0 13 Oct 2023
The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research Thomas Decker Ralf Gross Alexander Koebler Michael Lebacher Ronald Schnitzer Stefan H. Weber 31 2 0 11 Oct 2023
Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems Yuyuan Li Chaochao Chen Xiaolin Zheng Yizhao Zhang Zhongxuan Han Dan Meng Jun Wang MU 29 21 0 06 Oct 2023
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models Yongchan Kwon Eric Wu K. Wu James Zou DiffM TDI 18 53 0 02 Oct 2023
Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models Tianjian Li Haoran Xu Philipp Koehn Daniel Khashabi Kenton W. Murray 36 4 0 02 Oct 2023
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks Minh-Hao Van Alycia N. Carey Xintao Wu TDI AAML 8 2 0 15 Sep 2023
Natural Example-Based Explainability: a Survey Antonin Poché Lucas Hervier M. Bakkay XAI 26 11 0 05 Sep 2023
On the Cause of Unfairness: A Training Sample Perspective Yuanshun Yao Yang Liu TDI 31 0 0 30 Jun 2023
Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks Ziyi Huang H. Lam Haofeng Zhang UQCV 18 4 0 09 Jun 2023
Training Data Attribution for Diffusion Models Zheng Dai David K Gifford TDI 9 17 0 03 Jun 2023
A Bayesian Approach To Analysing Training Data Attribution In Deep Learning Elisa Nguyen Minjoon Seo Seong Joon Oh BDL 434 7 0 31 May 2023
Theoretical and Practical Perspectives on what Influence Functions Do Andrea Schioppa Katja Filippova Ivan Titov Polina Zablotskaia TDI 19 14 0 26 May 2023
How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning Rochelle Choenni Dan Garrette Ekaterina Shutova 32 15 0 22 May 2023
Class based Influence Functions for Error Detection Thang Nguyen-Duc Hoang Thanh-Tung Quan Hung Tran Huu-Tien Dang Nguyen Ngoc-Hieu An Dau Nghi D. Q. Bui TDI 22 1 0 02 May 2023
Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value Yongchan Kwon James Y. Zou TDI FedML 31 35 0 16 Apr 2023
AI Model Disgorgement: Methods and Choices Alessandro Achille Michael Kearns Carson Klingenberg Stefano Soatto MU 20 11 0 07 Apr 2023
GIF: A General Graph Unlearning Strategy via Influence Function Jiancan Wu Yi Yang Yuchun Qian Yongduo Sui Xiang Wang Xiangnan He MU 28 49 0 06 Apr 2023
Foundation Models and Fair Use Peter Henderson Xuechen Li Dan Jurafsky Tatsunori Hashimoto Mark A. Lemley Percy Liang 22 119 0 28 Mar 2023
TRAK: Attributing Model Behavior at Scale Sung Min Park Kristian Georgiev Andrew Ilyas Guillaume Leclerc A. Madry TDI 28 127 0 24 Mar 2023
Revisiting the Fragility of Influence Functions Jacob R. Epifano Ravichandran Ramachandran A. Masino Ghulam Rasool TDI 6 14 0 22 Mar 2023
Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values Adrián Arnaiz-Rodríguez Nuria Oliver FedML TDI 10 2 0 03 Mar 2023
Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets Irina Bejan Artem Sokolov Katja Filippova TDI 19 8 0 27 Feb 2023
Dataset Distillation with Convexified Implicit Gradients Noel Loo Ramin Hasani Mathias Lechner Daniela Rus DD 29 41 0 13 Feb 2023
Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning Maximilian Mozes Tolga Bolukbasi Ann Yuan Frederick Liu Nithum Thain Lucas Dixon 32 4 0 13 Feb 2023
Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data Jang-Hyun Kim Sangdoo Yun Hyun Oh Song 21 18 0 29 Jan 2023
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting P. Sattigeri S. Ghosh Inkit Padhi Pierre L. Dognin Kush R. Varshney FaML 25 28 0 13 Dec 2022
Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation Julius Adebayo M. Muelly H. Abelson Been Kim 16 86 0 09 Dec 2022
Training Data Influence Analysis and Estimation: A Survey Zayd Hammoudeh Daniel Lowd TDI 29 82 0 09 Dec 2022
A Flexible Nadaraya-Watson Head Can Offer Explainable and Calibrated Classification Alan Q. Wang M. Sabuncu 30 5 0 07 Dec 2022
Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases Mazda Moayeri Wenxiao Wang Sahil Singla S. Feizi 64 14 0 05 Dec 2022
Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States Ziqiao Wang Yongyi Mao 18 10 0 19 Nov 2022