Related papers: Statistically Testing Training Data for Unwanted E…

As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studies have empirically shown that training from scratch has the…

Research has shown that, machine learning models might inherit and propagate undesired social biases encoded in the data. To address this problem, fair training algorithms are developed. However, most algorithms assume we know…

The quality of underlying training data is very crucial for building performant machine learning models with wider generalizabilty. However, current machine learning (ML) tools lack streamlined processes for improving the data quality. So,…

Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…

Drift in machine learning refers to the phenomenon where the statistical properties of data or context, in which the model operates, change over time leading to a decrease in its performance. Therefore, maintaining a constant monitoring…

This paper investigates the application of machine learning when training a credit decision model over real, publicly available data whilst accounting for "bias objectives". We use the term "bias objective" to describe the requirement that…

The wide use of machine learning is fundamentally changing the software development paradigm (a.k.a. Software 2.0) where data becomes a first-class citizen, on par with code. As machine learning is used in sensitive applications, it becomes…

Creating resilient machine learning (ML) systems has become necessary to ensure production-ready ML systems that acquire user confidence seamlessly. The quality of the input data and the model highly influence the successful end-to-end…

Deep neural networks have been shown to learn and rely on spurious correlations present in the data that they are trained on. Reliance on such correlations can cause these networks to malfunction when deployed in the real world, where these…

We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to be forgotten."…

When mining large datasets in order to predict new data, limitations of the principles behind statistical machine learning pose a serious challenge not only to the Big Data deluge, but also to the traditional assumptions that data…

The problem of open-set noisy labels denotes that part of training data have a different label space that does not contain the true class. Lots of approaches, e.g., loss correction and label correction, cannot handle such open-set noisy…

Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female. Recently, fair representation learning (FRL) trained by deep neural networks has demonstrated superior…

We study the question of how well machine learning (ML) models trained on a certain data set provide privacy for the training data, or equivalently, whether it is possible to reverse-engineer the training data from a given ML model. While…

Modern machine learning methods often require more data for training than a single expert can provide. Therefore, it has become a standard procedure to collect data from external sources, e.g. via crowdsourcing. Unfortunately, the quality…

Modeling human ratings data subject to raters' decision uncertainty is an attractive problem in applied statistics. In view of the complex interplay between emotion and decision making in rating processes, final raters' choices seldom…

Artificial intelligence nowadays plays an increasingly prominent role in our life since decisions that were once made by humans are now delegated to automated systems. A machine learning algorithm trained based on biased data, however,…

Why do biased predictions arise? What interventions can prevent them? We evaluate 8.2 million algorithmic predictions of math performance from $\approx$400 AI engineers, each of whom developed an algorithm under a randomly assigned…

Machine learning systems are often trained using data collected from historical decisions. If past decisions were biased, then automated systems that learn from historical data will also be biased. We propose a black-box approach to…

Machine unlearning is an emerging field that selectively removes specific data samples from a trained model. This capability is crucial for addressing privacy concerns, complying with data protection regulations, and correcting errors or…