Related papers: Learning from Failure: Training Debiased Classifie…

Three classes of algorithms to learn the structure of Bayesian networks from data are common in the literature: constraint-based algorithms, which use conditional independence tests to learn the dependence structure of the data; score-based…

The predominant success of diffusion models in generative modeling has spurred significant interest in understanding their theoretical foundations. In this work, we propose a feature learning framework aimed at analyzing and comparing the…

Existing NLP datasets contain various biases that models can easily exploit to achieve high performances on the corresponding evaluation sets. However, focusing on dataset-specific biases limits their ability to learn more generalizable…

Deep neural networks are notoriously sensitive to spurious correlations - where a model learns a shortcut that fails out-of-distribution. Existing work on spurious correlations has often focused on incomplete correlations,leveraging access…

On the one hand, there has been considerable progress on neural network verification in recent years, which makes certifying neural networks a possibility. On the other hand, neural networks in practice are often re-trained over time to…

Most of today's distributed machine learning systems assume {\em reliable networks}: whenever two machines exchange information (e.g., gradients or models), the network should guarantee the delivery of the message. At the same time, recent…

Visual data from the Web power image classifiers, which often underpin many web services, such as recommendation and content moderation. However, the raw Web data often contain spurious correlations and social biases, and neural networks…

Simplicity bias poses a significant challenge in neural networks, often leading models to favor simpler solutions and inadvertently learn decision rules influenced by spurious correlations. This results in biased models with diminished…

It is not fully understood why adversarial examples can deceive neural networks and transfer between different networks. To elucidate this, several studies have hypothesized that adversarial perturbations, while appearing as noises, contain…

Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases. Adversarial learning may help models ignore sensitive biases and spurious correlations in data. We evaluate whether adversarial…

Due to their high degree of expressiveness, neural networks have recently been used as surrogate models for mapping inputs of an engineering system to outputs of interest. Once trained, neural networks are computationally inexpensive to…

Deep learning algorithms mine knowledge from the training data and thus would likely inherit the dataset's bias information. As a result, the obtained model would generalize poorly and even mislead the decision process in real-life…

Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand these factors, we…

Learning generalized models from biased data is an important undertaking toward fairness in deep learning. To address this issue, recent studies attempt to identify and leverage bias-conflicting samples free from spurious correlations…

We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and…

Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from…

A popular theory of perceptual processing holds that the brain learns both a generative model of the world and a paired recognition model using variational Bayesian inference. Most hypotheses of how the brain might learn these models assume…

We consider training a binary classifier under delayed feedback (\emph{DF learning}). For example, in the conversion prediction in online ads, we initially receive negative samples that clicked the ads but did not buy an item; subsequently,…

Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside. In this work, we demonstrate that there can exist a downside after all: bias…

One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest. The resulting failure to generalise cannot be…