Influence Functions in Deep Learning Are Fragile

25 June 2020

Papers citing "Influence Functions in Deep Learning Are Fragile"

50 / 154 papers shown

Title
Learning to Counterfactually Explain Recommendations Yuanshun Yao Chong Wang Hang Li CML OffRL 22 1 0 17 Nov 2022
Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations Shea Cardozo Gabriel Islas Montero Dmitry Kazhdan B. Dimanov Maleakhi A. Wijaya M. Jamnik Pietro Lio' AAML 20 0 0 14 Nov 2022
ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training Antonio Norelli Marco Fumero Valentino Maiorca Luca Moschella Emanuele Rodolà Francesco Locatello VLM 81 33 0 04 Oct 2022
Understanding Influence Functions and Datamodels via Harmonic Analysis Nikunj Saunshi Arushi Gupta M. Braverman Sanjeev Arora TDI 60 17 0 03 Oct 2022
Towards Faithful Model Explanation in NLP: A Survey Qing Lyu Marianna Apidianaki Chris Callison-Burch XAI 109 107 0 22 Sep 2022
If Influence Functions are the Answer, Then What is the Question? Juhan Bae Nathan Ng Alston Lo Marzyeh Ghassemi Roger C. Grosse TDI 16 88 0 12 Sep 2022
Leveraging Explanations in Interactive Machine Learning: An Overview Stefano Teso Öznur Alkan Wolfgang Stammer Elizabeth M. Daly XAI FAtt LRM 26 62 0 29 Jul 2022
JAWS: Auditing Predictive Uncertainty Under Covariate Shift Drew Prinster Anqi Liu S. Saria 11 11 0 21 Jul 2022
Understanding Instance-Level Impact of Fairness Constraints Jialu Wang X. Wang Yang Liu TDI FaML 12 33 0 30 Jun 2022
Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments Jinkun Lin Anqi Zhang Mathias Lécuyer Jinyang Li Aurojit Panda S. Sen TDI FedML 21 52 0 20 Jun 2022
Understanding Programmatic Weak Supervision via Source-aware Influence Function Jieyu Zhang Hong Wang Cheng-Yu Hsieh Alexander Ratner TDI 34 9 0 25 May 2022
ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data Xiaochuang Han Yulia Tsvetkov 19 27 0 25 May 2022
Towards Tracing Factual Knowledge in Language Models Back to the Training Data Ekin Akyürek Tolga Bolukbasi Frederick Liu Binbin Xiong Ian Tenney Jacob Andreas Kelvin Guu HILM 11 11 0 23 May 2022
Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees Jonathan Brophy Zayd Hammoudeh Daniel Lowd TDI 19 22 0 30 Apr 2022
Indiscriminate Data Poisoning Attacks on Neural Networks Yiwei Lu Gautam Kamath Yaoliang Yu AAML 28 24 0 19 Apr 2022
Deep Unlearning via Randomized Conditionally Independent Hessians Ronak R. Mehta Sourav Pal Vikas Singh Sathya Ravi MU 16 81 0 15 Apr 2022
Phenomenology of Double Descent in Finite-Width Neural Networks Sidak Pal Singh Aurélien Lucchi Thomas Hofmann Bernhard Schölkopf 13 10 0 14 Mar 2022
Understanding Rare Spurious Correlations in Neural Networks Yao-Yuan Yang Chi-Ning Chou Kamalika Chaudhuri AAML 16 25 0 10 Feb 2022
Approximating Full Conformal Prediction at Scale via Influence Functions Javier Abad Umang Bhatt Adrian Weller Giovanni Cherubin 29 10 0 02 Feb 2022
Datamodels: Predicting Predictions from Training Data Andrew Ilyas Sung Min Park Logan Engstrom Guillaume Leclerc A. Madry TDI 35 130 0 01 Feb 2022
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes Mazda Moayeri Phillip E. Pope Yogesh Balaji S. Feizi VLM 33 52 0 26 Jan 2022
Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation Zayd Hammoudeh Daniel Lowd TDI 18 28 0 25 Jan 2022
FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes Haonan Wang Ziwei Wu Jingrui He 19 12 0 15 Jan 2022
Consistent Approximations in Composite Optimization J. Royset 14 8 0 13 Jan 2022
Counterfactual Memorization in Neural Language Models Chiyuan Zhang Daphne Ippolito Katherine Lee Matthew Jagielski Florian Tramèr Nicholas Carlini 24 128 0 24 Dec 2021
Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime Rui Zhang Shihua Zhang TDI 19 21 0 15 Dec 2021
Scaling Up Influence Functions Andrea Schioppa Polina Zablotskaia David Vilar Artem Sokolov TDI 25 90 0 06 Dec 2021
SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning Vasisht Duddu S. Szyller Nadarajah Asokan 24 12 0 04 Dec 2021
ModelPred: A Framework for Predicting Trained Model from Training Data Yingyan Zeng Jiachen T. Wang Si-An Chen H. Just Ran Jin R. Jia TDI MU 25 2 0 24 Nov 2021
Revisiting Methods for Finding Influential Examples Karthikeyan K Anders Søgaard TDI 14 30 0 08 Nov 2021
Quantifying Epistemic Uncertainty in Deep Learning Ziyi Huang H. Lam Haofeng Zhang UQCV BDL UD PER 6 12 0 23 Oct 2021
Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks Shawn Shan A. Bhagoji Haitao Zheng Ben Y. Zhao AAML 86 50 0 13 Oct 2021
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates Xiaochuang Han Yulia Tsvetkov TDI 15 30 0 07 Oct 2021
Machine Unlearning of Features and Labels Alexander Warnecke Lukas Pirch Christian Wressnegger Konrad Rieck MU 6 171 0 26 Aug 2021
Seven challenges for harmonizing explainability requirements Jiahao Chen Victor Storchan 23 8 0 11 Aug 2021
Combining Feature and Instance Attribution to Detect Artifacts Pouya Pezeshkpour Sarthak Jain Sameer Singh Byron C. Wallace TDI 18 43 0 01 Jul 2021
Adversarial Examples Make Strong Poisons Liam H. Fowl Micah Goldblum Ping Yeh-Chiang Jonas Geiping Wojtek Czaja Tom Goldstein SILM 23 131 0 21 Jun 2021
On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation Wei Zhang Ziming Huang Yada Zhu Guangnan Ye Xiaodong Cui Fan Zhang 23 17 0 09 Jun 2021
Interactive Label Cleaning with Example-based Explanations Stefano Teso A. Bontempelli Fausto Giunchiglia Andrea Passerini 30 45 0 07 Jun 2021
On Memorization in Probabilistic Deep Generative Models G. V. D. Burg Christopher K. I. Williams TDI 20 58 0 06 Jun 2021
Locally Valid and Discriminative Prediction Intervals for Deep Learning Models Zhen Lin Shubhendu Trivedi Jimeng Sun 24 20 0 01 Jun 2021
An Empirical Comparison of Instance Attribution Methods for NLP Pouya Pezeshkpour Sarthak Jain Byron C. Wallace Sameer Singh TDI 13 35 0 09 Apr 2021
Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs Harini Suresh Kathleen M. Lewis John Guttag Arvind Satyanarayan FAtt 34 25 0 17 Feb 2021
Out-of-Distribution Generalization Analysis via Influence Function Haotian Ye Chuanlong Xie Yue Liu Zhenguo Li OOD 14 13 0 21 Jan 2021
Estimating informativeness of samples with Smooth Unique Information Hrayr Harutyunyan Alessandro Achille Giovanni Paolini Orchid Majumder Avinash Ravichandran Rahul Bhotika Stefano Soatto 16 24 0 17 Jan 2021
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging Han Guo Nazneen Rajani Peter Hase Mohit Bansal Caiming Xiong TDI 24 102 0 31 Dec 2020
LQF: Linear Quadratic Fine-Tuning Alessandro Achille Aditya Golatkar Avinash Ravichandran M. Polito Stefano Soatto 19 27 0 21 Dec 2020
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses Micah Goldblum Dimitris Tsipras Chulin Xie Xinyun Chen Avi Schwarzschild D. Song A. Madry Bo-wen Li Tom Goldstein SILM 13 270 0 18 Dec 2020
Quantizing data for distributed learning Osama A. Hanna Yahya H. Ezzeldin Christina Fragouli Suhas Diggavi FedML 39 20 0 14 Dec 2020
Data Appraisal Without Data Sharing Mimee Xu L. V. D. van der Maaten Awni Y. Hannun TDI 26 6 0 11 Dec 2020