SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.13368 · 2024

Unsupervised Concept Discovery Mitigates Spurious Correlations

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.13368")
get_code_for_paper("2402.13368")
have("2402.13368")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.13368.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.13368.svg)](https://syntology.ai/paper/2402.13368)

Connect an agent — have() is free.