Summary of A Simple Remedy For Dataset Bias Via Self-influence: a Mislabeled Sample Perspective, by Yeonsung Jung et al.
A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective
by Yeonsung Jung, Jaeyun Song, June Yong Yang, Jin-Hwa Kim, Sung-Yub Kim, Eunho Yang
First submitted to arxiv on: 1 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper tackles the crucial challenge of learning generalized models from biased data, a step towards fairness in deep learning. Recent studies attempt to identify and leverage bias-conflicting samples without prior knowledge of bias or an unbiased set. However, spurious correlation remains a significant issue due to difficulties in detecting these samples. The authors approach this challenge by applying Influence Function, a standard method for mislabeled sample detection, to identify bias-conflicting samples and propose a remedy for biased models. They demonstrate the effectiveness of their approach through comprehensive analysis and experiments on diverse datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us learn fair models from unfair data. Imagine you’re trying to train a machine learning model, but the training data is biased in some way. For example, if you’re trying to recognize faces, but the training data only includes pictures of people with light skin tones. This can lead to unfair results. The authors come up with a new way to detect these biases and correct them. They test their approach on different datasets and show that it works well. |
Keywords
» Artificial intelligence » Deep learning » Machine learning
