Related papers: Generating Skyline Datasets for Data Science Model…
Debiased recommendation with a randomized dataset has shown very promising results in mitigating the system-induced biases. However, it still lacks more theoretical insights or an ideal optimization objective function compared with the…
As the number of novel data-driven approaches to material science continues to grow, it is crucial to perform consistent quality, reliability and applicability assessments of model performance. In this paper, we benchmark the Materials…
Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive uncertainty estimation are still active areas of research.…
Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we present a novel…
The switch from a Model-Centric to a Data-Centric mindset is putting emphasis on data and its quality rather than algorithms, bringing forward new challenges. In particular, the sensitive nature of the information in highly regulated…
Dataset distillation (DD) aims to synthesize a small dataset whose test performance is comparable to a full dataset using the same model. State-of-the-art (SoTA) methods optimize synthetic datasets primarily by matching heuristic indicators…
Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting…
Machine Learning operations is unarguably a very important and also one of the hottest topics in Artificial Intelligence lately. Being able to define very clear hypotheses for actual real-life problems that can be addressed by machine…
Data compression is becoming critical for storing scientific data because many scientific applications need to store large amounts of data and post process this data for scientific discovery. Unlike image and video compression algorithms…
Methods of Machine and Deep Learning are gradually being integrated into industrial operations, albeit at different speeds for different types of industries. The aerospace and aeronautical industries have recently developed a roadmap for…
We propose Data Swarms, an algorithm to optimize the generation of synthetic evaluation data and advance quantitative desiderata of LLM evaluation. We first train a swarm of initial data generators using existing data, and define various…
Dataset distillation aims to synthesize a small dataset from a large dataset, enabling the model trained on it to perform well on the original dataset. With the blooming of large language models and multimodal large language models, the…
Ranking (or top-k) and skyline queries are the most popular approaches used to extract interesting data from large datasets. The first one is based on a scoring function to evaluate and rank tuples. Its computation is fast, but it is…
One of the main unsolved problems of cosmology is how to maximize the extraction of information from nonlinear data. If the data are nonlinear the usual approach is to employ a sequence of statistics (N-point statistics, counting statistics…
Imitation learning from large multi-task demonstration datasets has emerged as a promising path for building generally-capable robots. As a result, 1000s of hours have been spent on building such large-scale datasets around the globe.…
Performing data-intensive analytics is an essential part of modern Earth science. As such, research in atmospheric physics and meteorology frequently requires the processing of very large observational and/or modeled datasets. Typically,…
Conversion of raw data into insights and knowledge requires substantial amounts of effort from data scientists. Despite breathtaking advances in Machine Learning (ML) and Artificial Intelligence (AI), data scientists still spend the…
In a world where artificial intelligence and data science become omnipresent, data sharing is increasingly locking horns with data-privacy concerns. Differential privacy has emerged as a rigorous framework for protecting individual privacy…
Recently, various algorithms for data-driven simulation and control have been proposed based on the Willems' fundamental lemma. However, when collected data are noisy, these methods lead to ill-conditioned data-driven model structures. In…
Multi-objective optimization is the problem of optimizing simultaneously multiple objective functions and several techniques exist to deal with this problem. This paper aims to present the main methods that can be used to solve this issue…