Distributional robustness is a promising framework for training deep lea...
Many ML-based approaches have been proposed to automatically detect,
loc...
Deep learning (DL) models have become increasingly popular in identifyin...
Estimating the parameters of a probabilistic directed graphical model fr...
Self-supervised learning aims to extract meaningful features from unlabe...
Deep learning models, even the-state-of-the-art ones, are highly vulnera...
Hyperbolic geometry, a Riemannian manifold endowed with constant section...
Learning deep discrete latent presentations offers a promise of better
s...
Bayesian Neural Networks (BNNs) offer a probabilistic interpretation for...
Adversarial machine learning has been both a major concern and a hot top...
Online Class Incremental learning (CIL) is a challenging setting in Cont...
Multi-Task Learning (MTL) is a widely-used and powerful learning paradig...
Recently vision transformers (ViT) have been applied successfully for va...
Interpretable machine learning seeks to understand the reasoning process...
Software vulnerabilities existing in a program or function of computer
s...
Software vulnerabilities (SVs) have become a common, serious and crucial...
Interpretable machine learning offers insights into what factors drive a...
Modeling neural population dynamics underlying noisy single-trial spikin...
Sampling from an unnormalized target distribution is an essential proble...
Despite superior performance in many situations, deep neural networks ar...
It is well-known that deep neural networks (DNNs) are susceptible to
adv...
Domain adaptation (DA) benefits from the rigorous theoretical works that...
Deep Learning Recommendation Models (DLRM) are widespread, account for a...
Identifying vulnerabilities in the source code is essential to protect t...
We introduce a new dataset called SyntheticFur built specifically for ma...
Generating realistic sequences is a central task in many machine learnin...
There has been recently a growing interest in studying adversarial examp...
Mini-batch optimal transport (m-OT) has been successfully used in practi...
Contrastive learning (CL) has recently emerged as an effective approach ...
Medical image segmentation has played an important role in medical analy...
Interpretability and explainability of deep neural networks are challeng...
Training robust deep learning models for down-stream tasks is a critical...
Deep neural network image classifiers are reported to be susceptible to
...
Ensemble-based adversarial training is a principled approach to achieve
...
In this paper, we present a new topic modelling approach via the theory ...
The fact that deep neural networks are susceptible to crafted perturbati...
One of the challenging problems in sequence generation tasks is the opti...
Deep neural network image classifiers are reported to be susceptible to
...
Previous work has questioned the conditions under which the decision reg...
Deep domain adaptation has recently undergone a big success. Compared wi...
Generative Adversarial Networks (GANs) were intuitively and attractively...
Some real-world problems revolve to solve the optimization problem
_x∈Xf...
We propose in this paper a novel approach to tackle the problem of mode
...
Training model to generate data has increasingly attracted research atte...
We propose a new approach to train the Generative Adversarial Nets (GANs...
One of the most challenging problems in kernel online learning is to bou...