Estimating Training Data Influence by Tracing Gradient Descent

19 February 2020

Papers citing "Estimating Training Data Influence by Tracing Gradient Descent"

36 / 86 papers shown

Title
Influence Functions for Sequence Tagging Models Sarthak Jain Varun Manjunatha Byron C. Wallace A. Nenkova TDI 35 8 0 25 Oct 2022
SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval Kun Zhou Yeyun Gong Xiao Liu Wayne Xin Zhao Yelong Shen ... Jing Lu Rangan Majumder Ji-Rong Wen Nan Duan Weizhu Chen 44 33 0 21 Oct 2022
Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty Thomas George Guillaume Lajoie A. Baratin 34 5 0 19 Sep 2022
Mitigating Filter Bubbles within Deep Recommender Systems V. Anand Matthew Y. R. Yang Zhanzhan Zhao 18 2 0 16 Sep 2022
Understanding Instance-Level Impact of Fairness Constraints Jialu Wang Junfeng Fang Yang Liu TDI FaML 28 33 0 30 Jun 2022
Differentially Private Shapley Values for Data Evaluation Lauren Watson R. Andreeva Hao Yang Rik Sarkar TDI FAtt FedML 18 6 0 01 Jun 2022
Membership Inference Attack Using Self Influence Functions Gilad Cohen Raja Giryes TDI 32 12 0 26 May 2022
Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code Corpora An Dau Thang Nguyen-Duc Hoang Thanh-Tung Nghi D. Q. Bui TDI 18 4 0 25 May 2022
ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data Xiaochuang Han Yulia Tsvetkov 24 29 0 25 May 2022
Towards Computationally Feasible Deep Active Learning Akim Tsvigun Artem Shelmanov Gleb Kuzmin Leonid Sanochkin Daniil Larionov Gleb Gusev Manvel Avetisian L. Zhukov 32 15 0 07 May 2022
TracInAD: Measuring Influence for Anomaly Detection Hugo Thimonier Fabrice Popineau Arpad Rimmel Bich-Liên Doan Fabrice Daniel TDI 21 6 0 03 May 2022
Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees Jonathan Brophy Zayd Hammoudeh Daniel Lowd TDI 29 22 0 30 Apr 2022
An Empirical Study of Memorization in NLP Xiaosen Zheng Jing Jiang TDI 19 24 1 23 Mar 2022
Label-Free Explainability for Unsupervised Models Jonathan Crabbé M. Schaar FAtt MILM 24 22 0 03 Mar 2022
Human-Centered Concept Explanations for Neural Networks Chih-Kuan Yeh Been Kim Pradeep Ravikumar FAtt 42 26 0 25 Feb 2022
First is Better Than Last for Language Data Influence Chih-Kuan Yeh Ankur Taly Mukund Sundararajan Frederick Liu Pradeep Ravikumar TDI 34 20 0 24 Feb 2022
Competition-Level Code Generation with AlphaCode Yujia Li David Choi Junyoung Chung Nate Kushman Julian Schrittwieser ... Esme Sutherland Robson Pushmeet Kohli Nando de Koray Kavukcuoglu Oriol Vinyals 26 1,313 0 08 Feb 2022
Datamodels: Predicting Predictions from Training Data Andrew Ilyas Sung Min Park Logan Engstrom Guillaume Leclerc A. Madry TDI 52 131 0 01 Feb 2022
Rank List Sensitivity of Recommender Systems to Interaction Perturbations Sejoon Oh Berk Ustun Julian McAuley Srijan Kumar 30 34 0 29 Jan 2022
Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation Zayd Hammoudeh Daniel Lowd TDI 26 28 0 25 Jan 2022
Counterfactual Memorization in Neural Language Models Chiyuan Zhang Daphne Ippolito Katherine Lee Matthew Jagielski Florian Tramèr Nicholas Carlini 32 129 0 24 Dec 2021
Scaling Up Influence Functions Andrea Schioppa Polina Zablotskaia David Vilar Artem Sokolov TDI 33 91 0 06 Dec 2021
SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning Vasisht Duddu S. Szyller Nadarajah Asokan 32 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 33 2 0 24 Nov 2021
Revisiting Methods for Finding Influential Examples Karthikeyan K Anders Søgaard TDI 22 30 0 08 Nov 2021
Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods Peru Bhardwaj John D. Kelleher Luca Costabello Declan O’Sullivan 21 19 0 04 Nov 2021
Detecting Corrupted Labels Without Training a Model to Predict Zhaowei Zhu Zihao Dong Yang Liu NoLa 149 62 0 12 Oct 2021
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates Xiaochuang Han Yulia Tsvetkov TDI 31 30 0 07 Oct 2021
Learning to Synthesize Programs as Interpretable and Generalizable Policies Dweep Trivedi Jesse Zhang Shao-Hua Sun Joseph J. Lim NAI 24 72 0 31 Aug 2021
Influence-guided Data Augmentation for Neural Tensor Completion Sejoon Oh Sungchul Kim Ryan A. Rossi Srijan Kumar 28 10 0 23 Aug 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 33 17 0 09 Jun 2021
On Memorization in Probabilistic Deep Generative Models G. V. D. Burg Christopher K. I. Williams TDI 25 59 0 06 Jun 2021
HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations Weixin Liang Kai-Hui Liang Zhou Yu 42 15 0 01 Jun 2021
Machine Unlearning for Random Forests Jonathan Brophy Daniel Lowd MU 24 159 0 11 Sep 2020
What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation Vitaly Feldman Chiyuan Zhang TDI 46 443 0 09 Aug 2020
Influence Functions in Deep Learning Are Fragile S. Basu Phillip E. Pope S. Feizi TDI 37 220 0 25 Jun 2020