# FIB: A Method for Evaluation of Feature Impact Balance in Multi-Dimensional Data

arXiv: https://arxiv.org/abs/2207.04500 · HTML: https://mlsanity.com/paper/2207.04500/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 10 Jul 2022.

## Builds on (most cited first, 6 of 6)

- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/1901.11504/) (2019)
- [Few-Shot Learning via Learning the Representation, Provably](https://mlsanity.com/paper/2002.09434/) (2020)
- [Provable Meta-Learning of Linear Representations](https://mlsanity.com/paper/2002.11684/) (2020)
- [Predicting What You Already Know Helps: Provable Self-Supervised Learning](https://mlsanity.com/paper/2008.01064/) (2020)
- [Massively Multitask Networks for Drug Discovery](https://mlsanity.com/paper/1502.02072/) (2015)

## Abstract (arXiv)

Errors might not have the same consequences depending on the task at hand. Nevertheless, there is limited research investigating the impact of imbalance in the contribution of different features in an error vector. Therefore, we propose the Feature Impact Balance (FIB) score. It measures whether there is a balanced impact of features in the discrepancies between two vectors. We designed the FIB score to lie in [0, 1]. Scores close to 0 indicate that a small number of features contribute to most of the error, and scores close to 1 indicate that most features contribute to the error equally. We experimentally study the FIB on different datasets, using AutoEncoders and Variational AutoEncoders. We show how the feature impact balance varies during training and showcase its usability to support model selection for single output and multi-output tasks.