A hallmark of human intelligence is that we continue to learn new information and then extrapolate the learned onto tasks domains (see, e.g., Thrun Pratt (1998)). While this a fairly intuitive observation, formulating such ideas has proved be challenging research problem continues inspire studies. Recently, there been increasing interest in AI/ML about building models generalize across tasks, e...

Graph neural networks (GNNs) have achieved great success in node classification tasks. However, existing GNNs naturally bias towards the majority classes with more labelled data and ignore those minority relatively few ones. The traditional techniques often resort over-sampling methods, but they may cause overfitting problem. More recently, some works propose to synthesize additional nodes for ...

It is observed in the literature that data augmentation can significantly mitigate membership inference (MI) attack. However, this work, we challenge observation by proposing new MI attacks to utilize information of augmented data. attack widely used measure model's leakage training set. We establish optimal when model trained with data, which inspires us formulate as a set classification probl...

The progress in Query-focused Multi-Document Summarization (QMDS) has been limited by the lack of sufficient largescale high-quality training datasets. We present two QMDS datasets, which we construct using data augmentation methods: (1) transferring commonly used single-document CNN/Daily Mail summarization dataset to create QMDSCNN dataset, and (2) mining search-query logs QMDSIR dataset. The...

In this article, we introduce a new and efficient data augmentation approach to the posterior inference of models with shape parameters when reciprocal gamma function appears in full conditional densities. Our is approximate densities by using Gauss’s multiplication formula Stirling’s for function, where approximation error can be made arbitrarily small. We use techniques construct Gibbs Metrop...

Scarcity of training data is one the prominent problems for deep networks which require large amounts data. Data augmentation a widely used method to increase number samples and their variations. In this paper, we focus on improving vehicle detection performance in aerial images propose generative does not need any extra supervision than bounding box annotations objects dataset. The proposed in...

The goal of this work is to generate large statistically representative data sets train machine learning models for disruption prediction provided by from few existing discharges. Such a comprehensive training database important achieve satisfying and reliable results in artificial neural network classifiers. Here, we aim robust augmentation the multivariate time series using Student $t$ proces...