# RelatIF: Identifying Explanatory Training Examples via Relative Influence

arXiv: https://arxiv.org/abs/2003.11630 · HTML: https://mlsanity.com/paper/2003.11630/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2020.

## Built on by (most cited first, 28 of 28)

- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Interactive Label Cleaning with Example-based Explanations](https://mlsanity.com/paper/2106.03922/) (2021)
- [HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks](https://mlsanity.com/paper/2102.02515/) (2021)
- [Combining Feature and Instance Attribution to Detect Artifacts](https://mlsanity.com/paper/2107.00323/) (2021)
- [An Empirical Comparison of Instance Attribution Methods for NLP](https://mlsanity.com/paper/2104.04128/) (2021)
- [Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation](https://mlsanity.com/paper/2201.10055/) (2022)
- [Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates](https://mlsanity.com/paper/2110.03212/) (2021)
- [Repairing Neural Networks by Leaving the Right Past Behind](https://mlsanity.com/paper/2207.04806/) (2022)
- [Understanding Influence Functions and Datamodels via Harmonic Analysis](https://mlsanity.com/paper/2210.01072/) (2022)
- [Understanding Instance-based Interpretability of Variational Auto-Encoders](https://mlsanity.com/paper/2105.14203/) (2021)
- [Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets](https://mlsanity.com/paper/2302.13959/) (2023)
- [Contrastive Error Attribution for Finetuned Language Models](https://mlsanity.com/paper/2212.10722/) (2022)
- [How Many and Which Training Points Would Need to be Removed to Flip this Prediction?](https://mlsanity.com/paper/2302.02169/) (2023)
- [TracInAD: Measuring Influence for Anomaly Detection](https://mlsanity.com/paper/2205.01362/) (2022)
- [HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation](https://mlsanity.com/paper/2410.05090/) (2024)
- [DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction](https://mlsanity.com/paper/2303.01576/) (2023)
- [Generalizing Medical Image Representations via Quaternion Wavelet Networks](https://mlsanity.com/paper/2310.10224/) (2023)
- [Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning](https://mlsanity.com/paper/2302.06598/) (2023)
- [Large Language Model Sourcing: A Survey](https://mlsanity.com/paper/2510.10161/) (2025)
- [DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement](https://mlsanity.com/paper/2107.05978/) (2021)
- [Behavior of k-NN as an Instance-Based Explanation Method](https://mlsanity.com/paper/2109.06999/) (2021)
- [Additional Positive Enables Better Representation Learning for Medical Images](https://mlsanity.com/paper/2306.00112/) (2023)
- [AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations](https://mlsanity.com/paper/2407.16010/) (2024)
- [The Susceptibility of Example-Based Explainability Methods to Class Outliers](https://mlsanity.com/paper/2407.20678/) (2024)
- [A Bayesian Information-Theoretic Approach to Data Attribution](https://mlsanity.com/paper/2604.03858/) (2026)
- [Influence based explainability of brain tumors segmentation in multimodal Magnetic Resonance Imaging](https://mlsanity.com/paper/2405.12222/) (2024)
- [Global-to-Local Support Spectrums for Language Model Explainability](https://mlsanity.com/paper/2408.05976/) (2024)
- [Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes](https://mlsanity.com/paper/2511.17399/) (2025)

## Abstract (arXiv)

In this work, we focus on the use of influence functions to identify relevant training examples that one might hope "explain" the predictions of a machine learning model. One shortcoming of influence functions is that the training examples deemed most "influential" are often outliers or mislabelled, making them poor choices for explanation. In order to address this shortcoming, we separate the role of global versus local influence. We introduce RelatIF, a new class of criteria for choosing relevant training examples by way of an optimization objective that places a constraint on global influence. RelatIF considers the local influence that an explanatory example has on a prediction relative to its global effects on the model. In empirical evaluations, we find that the examples returned by RelatIF are more intuitive when compared to those found using influence functions.