Influence Functions in Deep Learning Are Fragile

25 June 2020

Papers citing "Influence Functions in Deep Learning Are Fragile"

50 / 154 papers shown

Title
MAGIC: Near-Optimal Data Attribution for Deep Learning Andrew Ilyas Logan Engstrom TDI 39 0 0 23 Apr 2025
Probabilistic Stability Guarantees for Feature Attributions Helen Jin Anton Xue Weiqiu You Surbhi Goel Eric Wong 19 0 0 18 Apr 2025
Detecting Instruction Fine-tuning Attack on Language Models with Influence Function Jiawei Li TDI AAML 33 0 0 12 Apr 2025
Data Poisoning in Deep Learning: A Survey Pinlong Zhao Weiyao Zhu Pengfei Jiao Di Gao Ou Wu AAML 39 0 0 27 Mar 2025
Finding the Muses: Identifying Coresets through Loss Trajectories M. Nagaraj Deepak Ravikumar Efstathia Soufleri Kaushik Roy 36 0 0 12 Mar 2025
$Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization$ Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$ -Constrained Optimization Xiaohua Feng Chao-Jun Chen Yuyuan Li L. Zhang Longfei Li Jun Zhou Xiaolin Zheng MU 70 0 0 20 Feb 2025
Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning L. Zhang Lijie Hu Di Wang LRM 92 0 0 17 Feb 2025
Dynamic Influence Tracker: Measuring Time-Varying Sample Influence During Training Jie Xu Zihan Wu TDI 50 0 0 15 Feb 2025
LiveVal: Time-aware Data Valuation via Adaptive Reference Points Jie Xu Zihan Wu Cong Wang Xiaohua Jia AI4TS 44 0 0 14 Feb 2025
Addressing Delayed Feedback in Conversion Rate Prediction via Influence Functions Chenlu Ding Jiancan Wu Yancheng Yuan Junfeng Fang Cunchun Li Xiang Wang Xiangnan He 69 1 0 01 Feb 2025
Most Influential Subset Selection: Challenges, Promises, and Beyond Yuzheng Hu Pingbang Hu Han Zhao Jiaqi W. Ma TDI 142 2 0 10 Jan 2025
Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models Yulei Qin Yuncheng Yang Pengcheng Guo Gang Li Hang Shao Yuchen Shi Zihan Xu Yun Gu Ke Li Xing Sun ALM 90 12 0 31 Dec 2024
Where Did Your Model Learn That? Label-free Influence for Self-supervised Learning Nidhin Harilal Amit Rege Reza Akbarian Bafghi M. Raissi C. Monteleoni TDI 41 0 0 22 Dec 2024
Unified Parameter-Efficient Unlearning for LLMs Chenlu Ding Jiancan Wu Yancheng Yuan Jinda Lu Kai Zhang Alex Su Xiang Wang Xiangnan He MU KELM 100 6 0 30 Nov 2024
Delta-Influence: Unlearning Poisons via Influence Functions Wenjie Li Jiawei Li Christian Schroeder de Witt Ameya Prabhu Amartya Sanyal TDI MU 92 0 0 20 Nov 2024
Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models Jinxu Lin Linwei Tao Minjing Dong Chang Xu TDI 38 2 0 24 Oct 2024
HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation Xinyu Zhou Simin Fan Martin Jaggi TDI 26 0 0 07 Oct 2024
$$\texttt{dattri}$: A Library for Efficient Data Attribution$ $\texttt{dattri}$ : A Library for Efficient Data Attribution Junwei Deng Ting-Wei Li Shiyuan Zhang Shixuan Liu Yijun Pan Hao Huang Xinhe Wang Pingbang Hu Xingjian Zhang Jiaqi W. Ma TDI 34 3 0 06 Oct 2024
How Much Can We Forget about Data Contamination? Sebastian Bordt Suraj Srinivas Valentyn Boreiko U. V. Luxburg 45 1 0 04 Oct 2024
Deep Unlearn: Benchmarking Machine Unlearning Xavier F. Cadet Anastasia Borovykh Mohammad Malekzadeh S. Ahmadi-Abhari Hamed Haddadi BDL MU 32 1 0 02 Oct 2024
Revisiting inverse Hessian vector products for calculating influence functions Yegor Klochkov Yang Liu TDI LLMSV 19 1 0 25 Sep 2024
Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI Elisa Nguyen Johannes Bertram Evgenii Kortukov Jean Y. Song Seong Joon Oh TDI 374 2 0 25 Sep 2024
Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models Yuncheng Yang Yulei Qin Tong Wu Zihan Xu Gang Li ... Yuchen Shi Ke Li Xing Sun Jie Yang Yun Gu ALM OffRL MoE 50 0 0 28 Aug 2024
Towards Certified Unlearning for Deep Neural Networks Binchi Zhang Yushun Dong Tianhao Wang Jundong Li MU 57 7 0 01 Aug 2024
Enhancing High-Energy Particle Physics Collision Analysis through Graph Data Attribution Techniques A. Verdone A. Devoto C. Sebastiani J. Carmignani M. D’Onofrio S. Giagu S. Scardapane M. Panella 37 0 0 20 Jul 2024
Data-Centric AI in the Age of Large Language Models Xinyi Xu Zhaoxuan Wu Rui Qiao Arun Verma Yao Shu ... Xiaoqiang Lin Wenyang Hu Zhongxiang Dai Pang Wei Koh Bryan Kian Hsiang Low ALM 44 2 0 20 Jun 2024
Selecting Interpretability Techniques for Healthcare Machine Learning models Daniel Sierra-Botero Ana Molina-Taborda Mario S. Valdés-Tresanco Alejandro Hernández-Arango Leonardo Espinosa-Leal Alexander Karpenko O. Lopez-Acevedo 23 0 0 14 Jun 2024
Ablation Based Counterfactuals Zheng Dai David K Gifford 21 0 0 12 Jun 2024
Causal Estimation of Memorisation Profiles Pietro Lesci Clara Meister Thomas Hofmann Andreas Vlachos Tiago Pimentel 45 5 0 06 Jun 2024
What is Dataset Distillation Learning? William Yang Ye Zhu Zhiwei Deng Olga Russakovsky DD 44 3 0 06 Jun 2024
Measuring Stochastic Data Complexity with Boltzmann Influence Functions Nathan Ng Roger C. Grosse Marzyeh Ghassemi 38 0 0 04 Jun 2024
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP S. Balasubramanian Samyadeep Basu S. Feizi CLIP 21 3 0 03 Jun 2024
Empirical influence functions to understand the logic of fine-tuning Jordan K Matelsky Lyle Ungar Konrad Paul Kording 26 0 0 01 Jun 2024
"Forgetting" in Machine Learning and Beyond: A Survey Alyssa Shuang Sha Bernardo Pereira Nunes Armin Haller MU KELM 38 1 0 31 May 2024
Salutary Labeling with Zero Human Annotation Wenxiao Xiao Hongfu Liu 21 0 0 27 May 2024
Efficient Ensembles Improve Training Data Attribution Junwei Deng Ting-Wei Li Shichang Zhang Jiaqi Ma TDI 30 2 0 27 May 2024
Editable Concept Bottleneck Models Lijie Hu Chenyang Ren Zhengyu Hu Cheng-Long Wang Di Wang Hui Xiong Jingfeng Zhang Di Wang 32 3 0 24 May 2024
What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions Sang Keun Choe Hwijeen Ahn Juhan Bae Kewen Zhao Minsoo Kang ... Teruko Mitamura Jeff Schneider Eduard Hovy Roger C. Grosse Eric P. Xing TDI 37 28 0 22 May 2024
DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning Zijian Zhou Xiaoqiang Lin Xinyi Xu Alok Prakash Daniela Rus K. H. Low 36 2 0 22 May 2024
Training Data Attribution via Approximate Unrolled Differentiation Juhan Bae Wu Lin Jonathan Lorraine Roger C. Grosse TDI MU 51 12 0 20 May 2024
Token-wise Influential Training Data Retrieval for Large Language Models Huawei Lin Jikai Long Zhaozhuo Xu Weijie Zhao 49 3 0 20 May 2024
Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models Anshuman Chhabra Bo Li Jian Chen Prasant Mohapatra Hongfu Liu TDI 29 0 0 06 May 2024
Neural Dynamic Data Valuation Zhangyong Liang Huanhuan Gao Ji Zhang TDI 40 1 0 30 Apr 2024
Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness Cheng-Long Wang Qi Li Zihang Xiang Yinzhi Cao Di Wang MU 21 1 0 19 Mar 2024
Shapley Values-Powered Framework for Fair Reward Split in Content Produced by GenAI Alex Glinsky Alexey Sokolsky 33 0 0 05 Mar 2024
Unveiling Privacy, Memorization, and Input Curvature Links Deepak Ravikumar Efstathia Soufleri Abolfazl Hashemi Kaushik Roy 49 5 0 28 Feb 2024
Variational Learning is Effective for Large Deep Networks Yuesong Shen Nico Daheim Bai Cong Peter Nickl Gian Maria Marconi ... Rio Yokota Iryna Gurevych Daniel Cremers Mohammad Emtiyaz Khan Thomas Möllenhoff 37 22 0 27 Feb 2024
InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks Somnath Banerjee Maulindu Sarkar Punyajoy Saha Binny Mathew Animesh Mukherjee TDI 34 0 0 22 Feb 2024
In-Context Learning Demonstration Selection via Influence Analysis Vinay M.S. Minh-Hao Van Xintao Wu 29 3 0 19 Feb 2024
The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes Myeongseob Ko Feiyang Kang Weiyan Shi Ming Jin Zhou Yu Ruoxi Jia TDI 16 4 0 14 Feb 2024