arXiv research

SCARY dataset generates complex causal scenarios for causality research.

Dependent MMD coresets help compare multiple related datasets.

MusPy is a toolkit for symbolic music generation, providing tools for dataset management and analysis.

The success of lottery ticket initializations (Frankle and Carbin, 2019) suggests that small, sparsified networks can be trained so long as the network is initialized appropriately. Unfortunately, finding these "winning ticket" initializations is computationally expensive. One potential solution is to reuse the same wi…

Framework generates multimodal datasets with known MI for benchmarking.

Generating datasets that "look like" given real ones is an interesting tasks for healthcare applications of ML and many other fields of science and engineering. In this paper we propose a new method of general application to binary datasets based on a method for learning the parameters of a latent variable moment that …

Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine learning. We present a weakly supervised algorithm for overcoming dataset bias for de…

LLMs can be influenced by unseen dataset subtexts, revealing new ways to select data subsets.

SVHN dataset's split affects generative models but not digit classification.

In this paper, we introduce the Fairness GAN, an approach for generating a dataset that is plausibly similar to a given multimedia dataset, but is more fair with respect to protected attributes in allocative decision making. We propose a novel auxiliary classifier GAN that strives for demographic parity or equality of …

Generative model tackles inconsistent attributes across datasets by enabling precise conditional generation.

Enhances machine learning with background knowledge through feature generation.

GANs trained on artificial datasets avoid dataset biases, revealing generative model weaknesses.

The paper bounds generalization errors for deep neural networks with Markov datasets.

Transformers fine-tuned on synthetic data boost tabular data classification performance.

Paper improves generalization bounds for multi-kernel learning with mixed datasets.

We prove Transformers can learn diverse Gröbner bases.

Boxhead dataset tests autoencoder disentanglement in hierarchical data.

Unsupervised method detects earthquakes from raw waveforms, generalizing across datasets.

Study improves interpretability in generative models by disentangling latent variables in scientific datasets.

Wittgenstein's Rule Following evolves datasets by extrapolating structural descriptors.

New framework transforms labeled datasets for various machine learning tasks.

Understanding if classifiers generalize to out-of-sample datasets is a central problem in machine learning. Microscopy images provide a standardized way to measure the generalization capacity of image classifiers, as we can image the same classes of objects under increasingly divergent, but controlled factors of variat…

In this paper, we propose a novel method for generating a synthetic dataset obeying Gaussian distribution. Compared to the commonly used benchmark datasets with unknown distribution, the synthetic dataset has an explicit distribution, i.e., Gaussian distribution. Meanwhile, it has the same characteristics as the benchm…

Generative model creates synthetic unlabeled data for SSL.

Augmentation improves machine learning model performance on small datasets.

An efficient learner is one who reuses what they already know to tackle a new problem. For a machine learner, this means understanding the similarities amongst datasets. In order to do this, one must take seriously the idea of working with datasets, rather than datapoints, as the key objects to model. Towards this goal…

Automatic speech emotion recognition provides computers with critical context to enable user understanding. While methods trained and tested within the same dataset have been shown successful, they often fail when applied to unseen datasets. To address this, recent work has focused on adversarial methods to find more g…

Paper tackles efficient risk estimation under dataset shift conditions.

Synthetic telematics dataset created from insurance claims data.

Large neural models have demonstrated human-level performance on language and vision benchmarks, while their performance degrades considerably on adversarial or out-of-distribution samples. This raises the question of whether these models have learned to solve a dataset rather than the underlying task by overfitting to…

Enhanced synthetic dataset improves asset allocation analysis.

Enhances anomaly detection using multiple reference datasets.

Generative adversarial networks (GANs) implicitly learn the probability distribution of a dataset and can draw samples from the distribution. This paper presents, Tabular GAN (TGAN), a generative adversarial network which can generate tabular data like medical or educational records. Using the power of deep neural netw…

YuruGAN generates yuru-chara images using GANs and clustering for small datasets.

Generative adversarial networks have been able to generate striking results in various domains. This generation capability can be general while the networks gain deep understanding regarding the data distribution. In many domains, this data distribution consists of anomalies and normal data, with the anomalies commonly…

BPVAE enhances VAE robustness to OOD inputs.

Clustering partitions a dataset such that observations placed together in a group are similar but different from those in other groups. Hierarchical and $K$-means clustering are two approaches but have different strengths and weaknesses. For instance, hierarchical clustering identifies groups in a tree-like structure b…

One of the impediments in advancing actuarial research and developing open source assets for insurance analytics is the lack of realistic publicly available datasets. In this work, we develop a workflow for synthesizing insurance datasets leveraging CTGAN, a recently proposed neural network architecture for generating …

Study reveals statistical bias in dataset replication, reducing accuracy drop from 11-14% to 3.6%.

In this paper, we propose a data collaboration analysis method for distributed datasets. The proposed method is a centralized machine learning while training datasets and models remain distributed over some institutions. Recently, data became large and distributed with decreasing costs of data collection. If we can cen…

Paper proposes HCDC to improve hyperparameter search efficiency.

OGB provides diverse graph datasets for robust ML research.

Method generates prototypes from small datasets for efficient learning.

FedSyn generates synthetic data from multiple organizations' datasets.

Quantum datasets improve QML performance.

Proposes a novel method to identify complex effects in multi-view datasets.

Generative adversarial networks create synthetic insurance datasets from confidential originals.