Related papers: MetamatBench: Integrating Heterogeneous Data, Comp…

Artificial intelligence (AI) and machine learning (ML) models in materials science are predominantly trained on ideal bulk crystals, limiting their transferability to real-world applications where surfaces, interfaces, and defects dominate.…

A consistent theme in software experimentation at Microsoft has been solving problems of experimentation at scale for a diverse set of products. Running experiments at scale (i.e., many experiments on many users) has become state of the art…

As data science and machine learning methods are taking on an increasingly important role in the materials research community, there is a need for the development of machine learning software tools that are easy to use (even for nonexperts…

Materials informatics (MI), emerging from the integration of materials science and data science, is expected to significantly accelerate material development and discovery. The data used in MI are derived from both computational and…

While Machine Learning (ML) technologies are widely adopted in many mission critical fields to support intelligent decision-making, concerns remain about system resilience against ML-specific security attacks and privacy breaches as well as…

Classification is a fundamental task in machine learning. While conventional methods-such as binary, multiclass, and multi-label classification-are effective for simpler problems, they may not adequately address the complexities of some…

Mechanical metamaterials leverage geometric design to achieve unconventional properties, such as high strength at low density, efficient wave guiding, and complex shape morphing. The ability to control shape changes builds on the complex…

Large Language Models (LLMs) have demonstrated remarkable abilities in scientific reasoning, yet their reasoning capabilities in materials science remain underexplored. To fill this gap, we introduce MatSciBench, a comprehensive…

Context. Advancements in Machine Learning (ML) are revolutionizing every application domain, driving unprecedented transformations and fostering innovation. However, despite these advances, several organizations are experiencing friction in…

In reality, learning from multi-view multi-label data inevitably confronts three challenges: missing labels, incomplete views, and non-aligned views. Existing methods mainly concern the first two and commonly need multiple assumptions to…

This systematic literature review examines the critical challenges and solutions related to scalability and maintainability in Machine Learning (ML) systems. As ML applications become increasingly complex and widespread across industries,…

Machine learning (ML) offers powerful methods for detecting and modeling associations often in data with large feature spaces and complex associations. Many useful tools/packages (e.g. scikit-learn) have been developed to make the various…

We introduce MLRC-Bench, a benchmark designed to quantify how effectively language agents can tackle challenging Machine Learning (ML) Research Competitions, with a focus on open research problems that demand novel methodologies. Unlike…

Machine Learning is transitioning from an art and science into a technology available to every developer. In the near future, every application on every platform will incorporate trained models to encode data-based decisions that would be…

We present the Open MatSci ML Toolkit: a flexible, self-contained, and scalable Python-based framework to apply deep learning models and methods on scientific data with a specific focus on materials science and the OpenCatalyst Dataset. Our…

Federated learning (FL) has drawn increasing attention owing to its potential use in large-scale industrial applications. Existing federated learning works mainly focus on model homogeneous settings. However, practical federated learning…

While generalization over tasks from easy to hard is crucial to profile language models (LLMs), the datasets with fine-grained difficulty annotations for each problem across a broad range of complexity are still blank. Aiming to address…

The ubiquitous role of the cyber-infrastructures, such as the WWW, provides myriad opportunities for machine learning and its broad spectrum of application domains taking advantage of digital communication. Pattern classification and…

Measurements are fundamental to knowledge creation in science, enabling consistent sharing of findings and serving as the foundation for scientific discovery. As machine learning systems increasingly transform scientific fields, the…

Understanding the quality of a performance evaluation metric is crucial for ensuring that model outputs align with human preferences. However, it remains unclear how well each metric captures the diverse aspects of these preferences, as…