Related papers: Adversarial Structured Prediction for Multivariate…
Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…
With the recent advances in machine learning, problems that traditionally would require accurate modeling to be solved analytically can now be successfully approached with data-driven strategies. Among these, computing the inverse…
We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we construct a convex surrogate that can be optimized via…
In this paper we propose the Structured Deep Neural Network (Structured DNN) as a structured and deep learning algorithm, learning to find the best structured object (such as a label sequence) given a structured input (such as a vector…
The ability to make zero-shot predictions about the fitness consequences of protein sequence changes with pre-trained machine learning models enables many practical applications. Such models can be applied for downstream tasks like genetic…
Automatic Essay Scoring (AES) is widely used to evaluate candidates for educational purposes. However, due to the lack of representative data, most existing AES systems are not robust, and their scoring predictions are biased towards the…
Robust adversarial reinforcement learning has emerged as an effective paradigm for training agents to handle uncertain disturbance in real environments, with critical applications in sequential decision-making domains such as autonomous…
Tree ensembles are one of the most widely used model classes. However, these models are susceptible to adversarial examples, i.e., slightly perturbed examples that elicit a misprediction. There has been significant research on designing…
Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…
Due to numerous breakthroughs in real-world applications brought by machine intelligence, deep neural networks (DNNs) are widely employed in critical applications. However, predictions of DNNs are easily manipulated with imperceptible…
Machine learning has emerged as a significant approach to efficiently tackle electronic structure problems. Despite its potential, there is less guarantee for the model to generalize to unseen data that hinders its application in real-world…
As one of data-driven approaches to computational mechanics in elasticity, this paper presents a method finding a bound for structural response, taking uncertainty in a material data set into account. For construction of an uncertainty set,…
Structural equation models (SEMs) are commonly used to study the structural relationship between observed variables and latent constructs. Recently, Bayesian fitting procedures for SEMs have received more attention thanks to their potential…
Modeling the behavior of stock price data has always been one of the challengeous applications of Artificial Intelligence (AI) and Machine Learning (ML) due to its high complexity and dependence on various conditions. Recent studies show…
The amount of freely available systems for automatic speech recognition (ASR) based on neural networks is growing steadily, with equally increasingly reliable predictions. However, the evaluation of trained models is typically exclusively…
In this dissertation, we focus on several important problems in structured prediction. In structured prediction, the label has a rich intrinsic substructure, and the loss varies with respect to the predicted label and the true label pair.…
Structured output prediction aims to learn a predictor to predict a structured output from a input data vector. The structured outputs include vector, tree, sequence, etc. We usually assume that we have a training set of input-output pairs…
Machine learning systems and also, specifically, automatic speech recognition (ASR) systems are vulnerable against adversarial attacks, where an attacker maliciously changes the input. In the case of ASR systems, the most interesting cases…
This paper is concerned with structured machine learning, in a supervised machine learning context. It discusses how to make joint structured learning on interdependent objects of different nature, as well as how to enforce logical…
Structured prediction involves learning to predict complex structures rather than simple scalar values. The main challenge arises from the non-Euclidean nature of the output space, which generally requires relaxing the problem formulation.…