Graph-structured data are pervasive in the real-world such as social networks, molecular graphs and transaction networks.

To evaluate the efficacy of federated learning for treatment response prediction in bipolar disorder, we developed a robust simulation pipeline encompassing synthetic data generation, neural network ...

Demographic bias gaps are closing in face recognition, but how training images are sourced is becoming the field’s biggest privacy fight.

Synthetic generation replicates key clinical patterns from real-world data, enabling valid analyses with fewer patients.

In an age where data drives decisions and automation defines excellence, the insurance industry stands at the cusp of a digital renaissance. At the ...

The particle physics department (DPNC) studies the fundamental structures and laws of nature from the largest dimensions in the Universe to the smallest of the microcosm by using three complementary ...

Gynecological cancers, including breast, ovarian, and cervical malignancies, account for a significant global health burden among women. The review outlines how a spectrum of machine learning (ML) ...

A recent study finds that AI usage tilts heavily toward men. Part of the reason: Women worried they might be penalized for using AI.

The machine learning model the team implemented overcame the challenge of limited data to incorporate the alpha conotoxins' amino acid sequences, secondary structure propensities and electrostatic ...

Large language models often give confident answers even when the question can’t be answered. New research shows these models ...