相关论文: Adversarial Structured Prediction for Multivariate…

Adversarial training, the process of training a deep learning model with adversarial data, is one of the most successful adversarial defense methods for deep learning models. We have found that the robustness to white-box attack of an…

This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performance, they are…

Machine learning systems regularly deal with structured data in real-world applications. Unfortunately, such data has been difficult to faithfully represent in a way that most machine learning techniques would expect, i.e. as a real-valued…

Quantifying the confidence (or conversely the uncertainty) of a prediction is a highly desirable trait of an automatic system, as it improves the robustness and usefulness in downstream tasks. In this paper we investigate confidence…

An adversarial autoencoder conditioned on known parameters of a physical modeling bowed string synthesizer is evaluated for use in parameter estimation and resynthesis tasks. Latent dimensions are provided to capture variance not explained…

Many sectors nowadays require accurate and coherent predictions across their organization to effectively operate. Otherwise, decision-makers would be planning using disparate views of the future, resulting in inconsistent decisions across…

Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systems with real language understanding abilities,…

We describe the line search used in the minimum error rate training algorithm MERT as the "inside score" of a weighted proof forest under a semiring defined in terms of well-understood operations from computational geometry. This conception…

Advances in robotics, artificial intelligence, and machine learning are ushering in a new age of automation, as machines match or outperform human performance. Machine intelligence can enable businesses to improve performance by reducing…

Structural health monitoring (SHM) is critical to safeguarding the safety and reliability of aerospace, civil, and mechanical infrastructure. Machine learning-based data-driven approaches have gained popularity in SHM due to advancements in…

Estimation of Markov Random Field and covariance models from high-dimensional data represents a canonical problem that has received a lot of attention in the literature. A key assumption, widely employed, is that of {\em sparsity} of the…

Robust training methods against perturbations to the input data have received great attention in the machine learning literature. A standard approach in this direction is adversarial training which learns a model using…

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the…

Multiclass neural network classifiers are typically trained using cross-entropy loss but evaluated using metrics derived from the confusion matrix, such as Accuracy, $F_\beta$-Score, and Matthews Correlation Coefficient. This mismatch…

Ensembling word embeddings to improve distributed word representations has shown good success for natural language processing tasks in recent years. These approaches either carry out straightforward mathematical operations over a set of…

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…

Detection of adversarial examples has been a hot topic in the last years due to its importance for safely deploying machine learning algorithms in critical applications. However, the detection methods are generally validated by assuming a…

Existing Vision-Language Models often struggle with complex, multi-question reasoning tasks where partial correctness is crucial for effective learning. Traditional reward mechanisms, which provide a single binary score for an entire…

Structured prediction energy networks (SPENs; Belanger & McCallum 2016) use neural network architectures to define energy functions that can capture arbitrary dependencies among parts of structured outputs. Prior work used gradient descent…

Learning models capable of providing reliable predictions in the face of adversarial actions has become a central focus of the machine learning community in recent years. This challenge arises from observing that data encountered at…