paper-with-me

Papers

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias

2023-05-30 · Yu Yang, Eric Gan, Gintare Karolina Dziugaite, Baharan Mirzasoleiman

Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly prone to learning spurious correlations in the training data, that may not hold at test time. In this work, we provide the first theoretical analysis of the effect of simplicity bias on learning spurious correlations. Notably, we show that examples with spurious features are provably separable based on the model's output early in training. We further illustrate that if spurious features have a small enough noise-to-signal ratio, the network's output on the majority of examples is almost exclusively determined by the spurious features, leading to poor worst-group test accuracy. Finally, we propose SPARE, which identifies spurious correlations early in training and utilizes importance sampling to alleviate their effect. Empirically, we demonstrate that SPARE outperforms state-of-the-art methods by up to 21.1% in worst-group accuracy, while being up to 12x faster. We also show that SPARE is a highly effective but lightweight method to discover spurious correlations.

📄 PDF Abstract BibTeX arXiv:2305.18761

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive Bias

Similar Papers 제목 키워드 기반

Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort

2024-07-12 · Jeeyung Kim, Ze Wang, Qiang Qiu

Enhancing model interpretability can address spurious correlations by revealing how models draw their predictions. Concept Bottleneck Models (CBMs) can provide a principled way of disclosing and guiding model behaviors t…

Causal-Ex: Causal Graph-based Micro and Macro Expression Spotting

2025-03-12 · Pei-Sze Tan, Sailaja Rajanala, Arghya Pal, Raphaël C. -W. Phan 외

Detecting concealed emotions within apparently normal expressions is crucial for identifying potential mental health issues and facilitating timely support and intervention. The task of spotting macro and micro-expressio…

Causal Inference

CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples

2025-08-26 · Kyohoon Jin, Juhwan Choi, Jungmin Yun, Junho Lee 외 arxiv

Deep learning models often learn and exploit spurious correlations in training data, using these non-target features to inform their predictions. Such reliance leads to performance degradation and poor generalization on …

Data Augmentation

Learning from Failure: Training Debiased Classifier from Biased Classifier

2020-07-06 · Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee 외

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on …

Action RecognitionFacial Attribute ClassificationOut-of-Distribution Generalization

Learning from Failure: De-biasing Classifier from Biased Classifier

2020-12-01 · NeurIPS 2020 12 · Junhyun Nam, Hyuntak Cha, Sung-Soo Ahn, Jaeho Lee 외

Neural networks often learn to make predictions that overly rely on spurious corre- lation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling o…