🏢 RWTH Aachen University
Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning
·1985 words·10 mins·
loading
·
loading
🏢 RWTH Aachen University
Data-driven approach corrects confidence intervals in high-dimensional learning, improving accuracy for various models and bridging theory and practice.
Graph Neural Networks Do Not Always Oversmooth
·1471 words·7 mins·
loading
·
loading
Machine Learning
Semi-Supervised Learning
🏢 RWTH Aachen University
Deep graph neural networks often suffer from oversmoothing; this paper reveals a non-oversmoothing phase controllable by weight variance, enabling deep, expressive models.