paper-with-me

Papers

MaskTune: Mitigating Spurious Correlations by Forcing to Explore

2022-09-30 · Saeid Asgari Taghanaki, Aliasghar Khani, Fereshte Khani, Ali Gholami, Linh Tran, Ali Mahdavi-Amiri, Ghassan Hamarneh

A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features. This work proposes MaskTune, a masking strategy that prevents over-reliance on spurious (or a limited number of) features. MaskTune forces the trained model to explore new features during a single epoch finetuning by masking previously discovered features. MaskTune, unlike earlier approaches for mitigating shortcut learning, does not require any supervision, such as annotating spurious features or labels for subgroup samples in a dataset. Our empirical results on biased MNIST, CelebA, Waterbirds, and ImagenNet-9L datasets show that MaskTune is effective on tasks that often suffer from the existence of spurious correlations. Finally, we show that MaskTune outperforms or achieves similar performance to the competing methods when applied to the selective classification (classification with rejection option) task. Code for MaskTune is available at https://github.com/aliasgharkhani/Masktune.

📄 PDF Abstract BibTeX arXiv:2210.00055

Code (1)

aliasgharkhani/masktune 공식 구현 pytorch

Similar Papers 제목 키워드 기반

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

2024-11-06 · Maya Varma, Jean-Benoit Delbrouck, Zhihong Chen, Akshay Chaudhari 외

Fine-tuned vision-language models (VLMs) often capture spurious correlations between image features and textual attributes, resulting in degraded zero-shot performance at test time. Existing approaches for addressing spu…

image-classificationImage Classificationzero-shot-classificationZero-Shot Learning

Mitigating Spurious Correlations for Self-supervised Recommendation

2022-12-08 · Xinyu Lin, Yiyan Xu, Wenjie Wang, Yang Zhang 외

Recent years have witnessed the great success of self-supervised learning (SSL) in recommendation systems. However, SSL recommender models are likely to suffer from spurious correlations, leading to poor generalization. …

Feature EngineeringRecommendation SystemsSelf-Supervised Learning

Explore Spurious Correlations at the Concept Level in Language Models for Text Classification

2023-11-15 · YuHang Zhou, Paiheng Xu, Xiaoyu Liu, Bang An 외

Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness…

counterfactualIn-Context Learningtext-classificationText Classification

Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning

2023-04-08 · Yu Yang, Besmira Nushi, Hamid Palangi, Baharan Mirzasoleiman

Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments. However, mitigating these correlations durin…

Attribute

Spuriousness-Aware Meta-Learning for Learning Robust Classifiers

2024-06-15 · Guangtao Zheng, Wenqian Ye, Aidong Zhang

Spurious correlations are brittle associations between certain attributes of inputs and target variables, such as the correlation between an image background and an object class. Deep image classifiers often leverage the…

AttributeLanguage ModellingMeta-Learning