Recently, there has been increasing interest in developing and deploying deep graph learning algorithms for various tasks, such as fraud detection and recommender systems. However, there is a limited number of publicly available graph-structured datasets, most of which are small compared with production-sized applications or limited in their application domain. In this work, we tackle this shortcoming by proposing a synthetic graph generation tool that enables scaling datasets to production-size graphs with trillions of edges and billions of nodes. The proposed method comprises a series of parametric models that can either be randomly initialized or fit to proprietary datasets. These models can then be released to researchers to study graph methods on the synthetic data, facilitating prototype development and novel applications. We demonstrate the generalizability of the framework across various datasets, mimicking their structural and feature distributions, as well as the ability to scale them to varying sizes, demonstrating their usefulness for benchmarking and model development. Code can be found on GitHub.

In many machine learning applications, we are faced with incomplete datasets. In the literature, missing data imputation techniques have been mostly concerned with filling missing values. However, the existence of missing values is synonymous with uncertainties not only over the distribution of missing values but also over target class assignments that require careful consideration. In this paper, we propose a simple and effective method for imputing missing features and estimating the distribution of target assignments given incomplete data. In order to make imputations, we train a simple and effective generator network to generate imputations that a discriminator network is tasked to distinguish. Following this, a predictor network is trained using the imputed samples from the generator network to capture the classification uncertainties and make predictions accordingly. The proposed method is evaluated on CIFAR-10 and MNIST image datasets as well as five real-world tabular classification datasets, under different missingness rates and structures. Our experimental results show the effectiveness of the proposed method in generating imputations as well as providing estimates for the class uncertainties in a classification task when faced with missing values.

Effective representation learning of electronic health records is a challenging task and is becoming more important as the availability of such data is becoming pervasive. The data contained in these records are irregular and contain multiple modalities such as notes, and medical codes. They are preempted by medical conditions the patient may have, and are typically recorded by medical staff. Accompanying codes are notes containing valuable information about patients beyond the structured information contained in electronic health records. We use transformer networks and the recently proposed BERT language model to embed these data streams into a unified vector representation. The presented approach effectively encodes a patient's visit data into a single a distributed representation, which can be used for downstream tasks. Our model demonstrates superior performance and generalization on mortality, readmission and length of stay tasks using the publicly available MIMIC-III ICU dataset.

In real-world scenarios, different features have different acquisition costs at test time which necessitates cost-aware methods to optimize the cost and performance tradeoff. This paper introduces a novel and scalable approach for cost-aware feature acquisition at test time. The method incrementally asks for features based on the available context that are known feature values. The proposed method is based on sensitivity analysis in neural networks and density estimation using denoising autoencoders with binary representation layers. In the proposed architecture, a denoising autoencoder is used to handle unknown features (i.e., features that are yet to be acquired), and the sensitivity of predictions with respect to each unknown feature is used as a context-dependent measure of informativeness. We evaluated the proposed method on eight different real-world data sets as well as one synthesized data set and compared its performance with several other approaches in the literature. According to the results, the suggested method is capable of efficiently acquiring features at test time in a cost- and context-aware fashion.