相关论文: Shortcut Mitigation via Spurious-Positive Samples

We describe and analyze algorithms for shape-constrained symbolic regression, which allows the inclusion of prior knowledge about the shape of the regression function. This is relevant in many areas of engineering -- in particular whenever…

Mislabeled, duplicated, or biased data in real-world scenarios can lead to prolonged training and even hinder model convergence. Traditional solutions prioritizing easy or hard samples lack the flexibility to handle such a variety…

Deep neural networks often learn and rely on spurious correlations, i.e., superficial associations between non-causal features and the targets. For instance, an image classifier may identify camels based on the desert backgrounds. While it…

When we can not assume a large amount of annotated data , active learning is a good strategy. It consists in learning a model on a small amount of annotated data (annotation budget) and in choosing the best set of points to annotate in…

Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…

Many problems in science and engineering require making predictions based on few observations. To build a robust predictive model, these sparse data may need to be augmented with simulated data, especially when the design space is…

Problems of segmentation, denoising, registration and 3D reconstruction are often addressed with the graph cut algorithm. However, solving an unconstrained graph cut problem is NP-hard. For tractable optimization, pairwise potentials have…

Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts. The presence of spurious correlations in training datasets leads ERM-trained models to…

Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explanations.This behavior leads to poor generalization when the learned explanations rely on spurious…

Deep learning models are known to overfit and memorize spurious features in the training dataset. While numerous empirical studies have aimed at understanding this phenomenon, a rigorous theoretical framework to quantify it is still…

In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels. This issue limits the robustness and generalization of models, especially when…

Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through an empirical study, we observe that responses with medium…

In microscopy image cell segmentation, it is common to train a deep neural network on source data, containing different types of microscopy images, and then fine-tune it using a support set comprising a few randomly selected and annotated…

Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data. The data representations are able to capture many underlying attributes of data, and be useful in downstream…

Machine-learning (ML) shortcuts or spurious correlations are artifacts in datasets that lead to very good training and test performance but severely limit the model's generalization capability. Such shortcuts are insidious because they go…

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. To mitigate spurious…

Acquiring and training on large-scale labeled data can be impractical due to cost constraints. Additionally, the use of small training datasets can result in considerable variability in model outcomes, overfitting, and learning of spurious…

Models trained with empirical risk minimization (ERM) are prone to be biased towards spurious correlations between target labels and bias attributes, which leads to poor performance on data groups lacking spurious correlations. It is…

Given a sample of size $N$, it is often useful to select a subsample of smaller size $n<N$ to be used for statistical estimation or learning. Such a data selection step is useful to reduce the requirements of data labeling and the…

Machine learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…