A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Data augmentation impacts adversarial risk; careful application recommended.
This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenting the original training data. Different from conventional data augmen…
Adversarial AutoAugment improves image classification with less computation.
Data augmentation improves robustness in adversarial training.
DRO-Augment framework enhances deep neural network robustness.
Augments graph node features to improve GNN performance.
Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given t…
The paper examines how adversarial training and noise affect neural network performance.
We propose a novel autoencoding model called Pairwise Augmented GANs. We train a generator and an encoder jointly and in an adversarial manner. The generator network learns to sample realistic objects. In turn, the encoder network at the same time is trained to map the true data distribution to the prior in latent spac…
Enhances neural network robustness with Mixup and TLAT.
GCNNs gain rotation invariance with more training augmentation, making SVD-Universal more effective.
Develops a framework for assessing adversarial robustness in deep learning models.
RIA method improves OoD generalization for covariate shift.
CEB enhances model resilience through simple entropy bottleneck.
Generative data augmentation boosts learning performance in various tasks.
In this paper we propose a new augmentation technique, called patch augmentation, that, in our experiments, improves model accuracy and makes networks more robust to adversarial attacks. In brief, this data-independent approach creates new image data based on image/label pairs, where a patch from one of the two images …
We propose a novel adversarial learning strategy for mixture models of Hawkes processes, leveraging data augmentation techniques of Hawkes process in the framework of self-paced learning. Instead of learning a mixture model directly from a set of event sequences drawn from different Hawkes processes, the proposed metho…
This paper proposes CSADA to make DNNs cost-sensitive.
Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing robust features such as binarization, e.g., rounding, and group extraction, e.g…
Adversarial training improves robustness against common corruptions.
We propose regularization strategies for learning discriminative models that are robust to in-class variations of the input data. We use the Wasserstein-2 geometry to capture semantically meaningful neighborhoods in the space of images, and define a corresponding input-dependent additive noise data augmentation model. …
LcGAN generates synthetic CT images for hemorrhagic lesion segmentation.
Paper proposes a method to train robust neural networks without labeled data.
MEMGAN uses memory to improve anomaly detection by isolating abnormal data.
Enhances adversarial robustness with unlabeled out-of-domain data.
Mixup improves model robustness and generalization by convexly combining examples.
With the advent of Deep Learning (DL) techniques, especially Generative Adversarial Networks (GANs), data augmentation and generation are quickly evolving domains that have raised much interest recently. However, the DL techniques are data demanding and since, medical data is not easily accessible, they suffer from dat…
Computer-aided breast cancer diagnosis in mammography is limited by inadequate data and the similarity between benign and cancerous masses. To address this, we propose a signed graph regularized deep neural network with adversarial augmentation, named \textsc{DiagNet}. Firstly, we use adversarial learning to generate p…
The paper introduces boundary thickness as a measure for improving model robustness.
ViewFool identifies adversarial viewpoints to test image recognition robustness.
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances …
Deep neural networks suffer from over-fitting and catastrophic forgetting when trained with small data. One natural remedy for this problem is data augmentation, which has been recently shown to be effective. However, previous works either assume that intra-class variances can always be generalized to new classes, or e…
AugmentedPCA improves PCA with supervised or adversarial objectives.
The pursuit of explaining and improving generalization in deep learning has elicited efforts both in regularization techniques as well as visualization techniques of the loss surface geometry. The latter is related to the intuition prevalent in the community that flatter local optima leads to lower generalization error…
MET learns tabular data representations without data augmentations.
GeoECG augments ECG data to improve heart disease detection.
Machine Learning (ML) models are applied in a variety of tasks such as network intrusion detection or Malware classification. Yet, these models are vulnerable to a class of malicious inputs known as adversarial examples. These are slightly perturbed inputs that are classified incorrectly by the ML model. The mitigation…
Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heuristic transformations, like geometric or color transformations. Instead of using predefined transformations, our work learns data augmentati…
One of the big restrictions in brain computer interface field is the very limited training samples, it is difficult to build a reliable and usable system with such limited data. Inspired by generative adversarial networks, we propose a conditional Deep Convolutional Generative Adversarial (cDCGAN) Networks method to ge…
Study shows GAN and GMM data augmentation improves AF signal classification accuracy.
Generative Adversarial Networks create realistic brain MRI images.
Study improves image classifier robustness to random p-norm corruptions.
Adversarial examples are augmented data points generated by imperceptible perturbation of input samples. They have recently drawn much attention with the machine learning and data mining community. Being difficult to distinguish from real examples, such adversarial examples could change the prediction of many of the be…
GANs can bias synthetic data, affecting minority and female faces.
GANs improve anomaly detection in power plants, achieving nearly perfect classification.
In this paper we propose a data augmentation method for time series with irregular sampling, Time-Conditional Generative Adversarial Network (T-CGAN). Our approach is based on Conditional Generative Adversarial Networks (CGAN), where the generative step is implemented by a deconvolutional NN and the discriminative step…
Generative Adversarial Networks create synthetic data for structural damage detection.
We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and validate its performance against a number of distortion types and transformations i…