Related papers: DataRater: Meta-Learned Dataset Curation

It is well known that the quality and quantity of training data are significant factors which affect the development and performance of machine intelligence algorithms. Without representative data, neither scientists nor algorithms would be…

Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There…

Most machine learning models require many iterations of hyper-parameter tuning, feature engineering, and debugging to produce effective results. As machine learning models become more complicated, this pipeline becomes more difficult to…

Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with many hyperparameters. Nevertheless, existing approaches are…

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural…

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…

Lack of data on which to perform experimentation is a recurring issue in many areas of research, particularly in machine learning. The inability of most automated data mining techniques to be generalized to all types of data is inherently…

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process,…

Much of the work in metalearning has focused on classifier selection, combined more recently with hyperparameter optimization, with little concern for data preprocessing. Yet, it is generally well accepted that machine learning applications…

Filter pruning is effective to reduce the computational costs of neural networks. Existing methods show that updating the previous pruned filter would enable large model capacity and achieve better performance. However, during the iterative…

NLP community is currently investing a lot more research and resources into development of deep learning models than training data. While we have made a lot of progress, it is now clear that our models learn all kinds of spurious patterns,…

Over the past years, there has been many efforts to curate and increase the added value of the raw data. Data curation has been defined as activities and processes an analyst undertakes to transform the raw data into contextualized data and…

As with any task, the process of building machine learning models can benefit from prior experience. Meta-learning for classifier selection leverages knowledge about the characteristics of different datasets and/or the past performance of…

Modern self-driving autonomy systems heavily rely on deep learning. As a consequence, their performance is influenced significantly by the quality and richness of the training data. Data collecting platforms can generate many hours of raw…

In the current landscape of foundation model training, there is a significant reliance on public domain data, which is nearing exhaustion according to recent research. To further scale up, it is crucial to incorporate collaboration among…

Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper…

High-dimensional tensor models are notoriously computationally expensive to train. We present a meta-learning algorithm, MMT, that can significantly speed up the process for spatial tensor models. MMT leverages the property that spatial…

The quality of the data in a dataset can have a substantial impact on the performance of a machine learning model that is trained and/or evaluated using the dataset. Effective dataset management, including tasks such as data cleanup,…

Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work…