Unsupervised Concept Discovery Mitigates Spurious Correlations
ICLM 2024 Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases. Addressing this challenge typically involves methods relying on prior knowledge and group annotation to remove spurious correlations, which may not be readily available...
Saved in:
Main Authors | , , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
20.02.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | ICLM 2024 Models prone to spurious correlations in training data often produce brittle
predictions and introduce unintended biases. Addressing this challenge
typically involves methods relying on prior knowledge and group annotation to
remove spurious correlations, which may not be readily available in many
applications. In this paper, we establish a novel connection between
unsupervised object-centric learning and mitigation of spurious correlations.
Instead of directly inferring subgroups with varying correlations with labels,
our approach focuses on discovering concepts: discrete ideas that are shared
across input samples. Leveraging existing object-centric representation
learning, we introduce CoBalT: a concept balancing technique that effectively
mitigates spurious correlations without requiring human labeling of subgroups.
Evaluation across the benchmark datasets for sub-population shifts demonstrate
superior or competitive performance compared state-of-the-art baselines,
without the need for group annotation. Code is available at
https://github.com/rarefin/CoBalT. |
---|---|
DOI: | 10.48550/arxiv.2402.13368 |