English
Related papers

Related papers: InfFeed: Influence Functions as a Feedback to Impr…

200 papers

Labeling bias arises during data collection due to resource limitations or unconscious bias, leading to unequal label error rates across subgroups or misrepresentation of subgroup prevalence. Most fairness constraints assume training labels…

Machine Learning · Computer Science 2026-02-24 Frida Jørgensen , Nina Weng , Siavash Bigdeli

Data-centric learning seeks to improve model performance from the perspective of data quality, and has been drawing increasing attention in the machine learning community. Among its key tools, influence functions provide a powerful…

Machine Learning · Computer Science 2025-10-07 Shahriar Kabir Nahin , Wenxiao Xiao , Joshua Liu , Anshuman Chhabra , Hongfu Liu

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

Influence functions efficiently estimate the effect of removing a single training data point on a model's learned parameters. While influence estimates align well with leave-one-out retraining for linear models, recent works have shown this…

Machine Learning · Computer Science 2022-09-13 Juhan Bae , Nathan Ng , Alston Lo , Marzyeh Ghassemi , Roger Grosse

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

With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influential group of training samples in a particular test…

Machine Learning · Computer Science 2020-07-08 Samyadeep Basu , Xuchen You , Soheil Feizi

Machine learning systems such as large scale recommendation systems or natural language processing systems are usually trained on billions of training points and are associated with hundreds of billions or trillions of parameters. Improving…

Machine Learning · Computer Science 2023-05-26 Michael Kounavis , Ousmane Dia , Ilqar Ramazanli

Influence functions (IF) have been seen as a technique for explaining model predictions through the lens of the training data. Their utility is assumed to be in identifying training examples "responsible" for a prediction so that, for…

Machine Learning · Computer Science 2023-05-29 Andrea Schioppa , Katja Filippova , Ivan Titov , Polina Zablotskaia

Influence function, a technique rooted in robust statistics, has been adapted in modern machine learning for a novel application: data attribution -- quantifying how individual training data points affect a model's predictions. However, the…

Machine Learning · Computer Science 2024-12-03 Junwei Deng , Weijing Tang , Jiaqi W. Ma

Human data annotation, especially when involving experts, is often treated as an objective reference. However, many annotation tasks are inherently subjective, and annotators' judgments may evolve over time. This study investigates changes…

Influence functions provide a principled method to assess the contribution of individual training samples to a specific target. Yet, their high computational costs limit their applications on large-scale models and datasets. Existing…

Machine Learning · Computer Science 2025-06-27 Xinyu Zhou , Simin Fan , Martin Jaggi

Data annotated by humans is a source of knowledge by describing the peculiarities of the problem and therefore fueling the decision process of the trained model. Unfortunately, the annotation process for subjective natural language…

Computation and Language · Computer Science 2023-12-14 Kamil Kanclerz , Julita Bielaniewicz , Marcin Gruza , Jan Kocon , Stanisław Woźniak , Przemysław Kazienko

When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated risks, a potentially valuable source of evidence is: which training examples most contribute to a given behavior?…

We present the first use of influence functions for deep learning-based wireless receivers. Applied to DeepRx, a fully convolutional receiver, influence analysis reveals which training samples drive bit predictions, enabling targeted…

Machine Learning · Computer Science 2026-01-22 Marko Tuononen , Heikki Penttinen , Ville Hautamäki

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…

Influence functions are important for quantifying the impact of individual training data points on a model's predictions. Although extensive research has been conducted on influence functions in traditional machine learning models, their…

Computation and Language · Computer Science 2024-12-23 Zhe Li , Wei Zhao , Yige Li , Jun Sun

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

Widespread adoption of deep models has motivated a pressing need for approaches to interpret network outputs and to facilitate model debugging. Instance attribution methods constitute one means of accomplishing these goals by retrieving…

Computation and Language · Computer Science 2021-04-12 Pouya Pezeshkpour , Sarthak Jain , Byron C. Wallace , Sameer Singh

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

Sequential recommendation approaches have demonstrated remarkable proficiency in modeling user preferences. Nevertheless, they are susceptible to profile pollution attacks (PPA), wherein items are introduced into a user's interaction…

Information Retrieval · Computer Science 2024-12-03 Xiaoyu Du , Yingying Chen , Yang Zhang , Jinhui Tang