Related papers: Cold Case: The Lost MNIST Digits

In this paper, we study the problems in the discrete Fourier transform (DFT) test included in NIST SP 800-22 released by the National Institute of Standards and Technology (NIST), which is a collection of tests for evaluating both physical…

Many commercial and open-source models claim to detect machine-generated text with extremely high accuracy (99% or more). However, very few of these detectors are evaluated on shared benchmark datasets and even when they are, the datasets…

MindBigData 2023 MNIST-8B is the largest, to date (June 1st 2023), brain signals open dataset created for Machine Learning, based on EEG signals from a single subject captured using a custom 128 channels device, replicating the full 70,000…

Many software engineering research papers rely on time-based data (e.g., commit timestamps, issue report creation/update/close dates, release dates). Like most real-world data however, time-based data is often dirty. To date, there are no…

The aim of this work is to study the evolution of password selection among users. We investigate whether users follow best practices when selecting passwords and identify areas in need of improvement. Four distinct publicly-available…

Context: Data mining techniques have demonstrated to be a powerful technique for discovering insights hidden in data from a domain. However, these techniques demand very specialised skills. People willing to analyse data often lack these…

Many backdoor removal techniques in machine learning models require clean in-distribution data, which may not always be available due to proprietary datasets. Model inversion techniques, often considered privacy threats, can reconstruct…

Model checklists (Ribeiro et al., 2020) have emerged as a useful tool for understanding the behavior of LLMs, analogous to unit-testing in software engineering. However, despite datasets being a key determinant of model behavior, evaluating…

Quantum machine learning carries the promise to revolutionize information and communication technologies. While a number of quantum algorithms with potential exponential speedups have been proposed already, it is quite difficult to provide…

Person re-identification (re-ID) in the scenario with large spatial and temporal spans has not been fully explored. This is partially because that, existing benchmark datasets were mainly collected with limited spatial and temporal ranges,…

Dataset distillation is attracting more attention in machine learning as training sets continue to grow and the cost of training state-of-the-art models becomes increasingly high. By synthesizing datasets with high information density,…

Deep neural network architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial…

Dataset Distillation (DD) seeks to create a condensed dataset that, when used to train a model, enables the model to achieve performance similar to that of a model trained on the entire original dataset. It relieves the model training from…

With the move towards open research information, the DOI registration agency DataCite is increasingly used as a source for metadata describing research data, for example to perform scientometric analyses. However, there is a lack of…

In this work, we try to decipher the internal connection of NLP technology development in the past decades, searching for essence, which rewards us with a (potential) new learning paradigm for NLP tasks, dubbed as reStructured Pre-training…

Results of simulation studies evaluating the performance of statistical methods are often considered actionable and thus can have a major impact on the way empirical research is implemented. However, so far there is limited evidence about…

While fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models. Specifically, for tasks that take two inputs and require the…

Existing distantly supervised relation extractors usually rely on noisy data for both model training and evaluation, which may lead to garbage-in-garbage-out systems. To alleviate the problem, we study whether a small clean dataset could…

Multi-contrast magnetic resonance imaging (MRI) is widely used in clinical practice as each contrast provides complementary information. However, the availability of each imaging contrast may vary amongst patients, which poses challenges to…

Split learning is a collaborative learning design that allows several participants (clients) to train a shared model while keeping their datasets private. Recent studies demonstrate that collaborative learning models, specifically federated…