English
Related papers

Related papers: A Versatile Influence Function for Data Attributio…

200 papers

A critical aspect of analyzing and improving modern machine learning systems lies in understanding how individual training examples influence a model's predictive behavior. Estimating this influence enables critical applications, including…

Machine Learning · Computer Science 2025-10-15 Narine Kokhlikyan , Kamalika Chaudhuri , Saeed Mahloujifar

Causal influence measures for machine learnt classifiers shed light on the reasons behind classification, and aid in identifying influential input features and revealing their biases. However, such analyses involve evaluating the classifier…

Machine Learning · Computer Science 2018-04-10 Shayak Sen , Piotr Mardziel , Anupam Datta , Matthew Fredrikson

Influence Functions are a standard tool for attributing predictions to training data in a principled manner and are widely used in applications such as data valuation and fairness. In this work, we present realistic incentives to manipulate…

Machine Learning · Computer Science 2024-10-08 Chhavi Yadav , Ruihan Wu , Kamalika Chaudhuri

Estimators based on influence functions (IFs) have been shown to be effective in many settings, especially when combined with machine learning techniques. By focusing on estimating a specific target of interest (e.g., the average effect of…

Methodology · Statistics 2019-10-29 Aaron Fisher , Edward H. Kennedy

Influence functions estimate the effect of removing a training point on a model without the need to retrain. They are based on a first-order Taylor approximation that is guaranteed to be accurate for sufficiently small changes to the model,…

Machine Learning · Computer Science 2019-11-22 Pang Wei Koh , Kai-Siang Ang , Hubert H. K. Teo , Percy Liang

Both classification and regression tasks are susceptible to the biased distribution of training data. However, existing approaches are focused on the class-imbalanced learning and cannot be applied to the problems of numerical regression…

Machine Learning · Computer Science 2021-09-15 Wentai Wu , Ligang He , Weiwei Lin

Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs. Existing methods for diffusion models typically require access to model gradients or retraining, limiting their…

Machine Learning · Computer Science 2025-10-17 Yutian Zhao , Chao Du , Xiaosen Zheng , Tianyu Pang , Min Lin

The instrumental variable (IV) approach is commonly used to infer causal effects in the presence of unmeasured confounding. Existing methods typically aim to estimate the mean causal effects, whereas a few other methods focus on quantile…

Methodology · Statistics 2025-03-13 Anastasiia Holovchak , Sorawit Saengkyongam , Nicolai Meinshausen , Xinwei Shen

As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by…

Fairness in machine learning has attained significant focus due to the widespread application in high-stake decision-making tasks. Unregulated machine learning classifiers can exhibit bias towards certain demographic groups in data, thus…

Machine Learning · Computer Science 2023-07-04 Bishwamittra Ghosh , Debabrota Basu , Kuldeep S. Meel

Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we provide an explanation for the instability of IFs and…

Computation and Language · Computer Science 2023-05-03 Thang Nguyen-Duc , Hoang Thanh-Tung , Quan Hung Tran , Dang Huu-Tien , Hieu Ngoc Nguyen , Anh T. V. Dau , Nghi D. Q. Bui

Statistical models are central to machine learning with broad applicability across a range of downstream tasks. The models are controlled by free parameters that are typically estimated from data by maximum-likelihood estimation or…

Machine Learning · Computer Science 2023-08-16 Vaidotas Simkus , Benjamin Rhodes , Michael U. Gutmann

Feature selection is one of the most relevant processes in any methodology for creating a statistical learning model. Usually, existing algorithms establish some criterion to select the most influential variables, discarding those that do…

Machine Learning · Statistics 2024-05-10 Carlos Sebastián , Carlos E. González-Guillén

Influence functions estimate effect of individual data points on predictions of the model on test data and were adapted to deep learning in Koh and Liang [2017]. They have been used for detecting data poisoning, detecting helpful and…

Machine Learning · Computer Science 2022-10-04 Nikunj Saunshi , Arushi Gupta , Mark Braverman , Sanjeev Arora

As the complexity of machine learning (ML) models increases, resulting in a lack of prediction explainability, several methods have been developed to explain a model's behavior in terms of the training data points that most influence the…

Machine Learning · Computer Science 2021-07-14 Umang Bhatt , Isabel Chien , Muhammad Bilal Zafar , Adrian Weller

Collaborative Filtering (CF) models, despite their great success, suffer from severe performance drops due to popularity distribution shifts, where these changes are ubiquitous and inevitable in real-world scenarios. Unfortunately, most…

Information Retrieval · Computer Science 2023-05-19 An Zhang , Jingnan Zheng , Xiang Wang , Yancheng Yuan , Tat-Seng Chua

Traditional data influence estimation methods, like influence function, assume that learning algorithms are permutation-invariant with respect to training data. However, modern training paradigms, especially for foundation models using…

Machine Learning · Computer Science 2024-12-13 Jiachen T. Wang , Dawn Song , James Zou , Prateek Mittal , Ruoxi Jia

Diffusion policies are becoming mainstream in robotic manipulation but suffer from hard negative class imbalance due to uniform sampling and lack of sample difficulty awareness, leading to slow training convergence and frequent inference…

Robotics · Computer Science 2026-04-20 Xinglei Yu , Zhenyang Liu , Shufeng Nan , Simo Wu , Yanwei Fu

Vertical federated learning trains models from feature-partitioned datasets across multiple clients, who collaborate without sharing their local data. Standard approaches assume that all feature partitions are available during both training…

Machine Learning · Computer Science 2025-04-23 Pedro Valdeira , Shiqiang Wang , Yuejie Chi

Influence functions (IFs) elucidate how training data changes model behavior. However, the increasing size and non-convexity in large-scale models make IFs inaccurate. We suspect that the fragility comes from the first-order approximation…

Machine Learning · Computer Science 2024-05-07 Hyeonsu Lyu , Jonggyu Jang , Sehyun Ryu , Hyun Jong Yang