3 papers
cs.LG2025
Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information
Yuan Cheng, Yu Huang, Zhe Xiong +2
Uncovering hidden graph structures underlying real-world data is a critical challenge with broad applications across scientific domains. Recently, transformer-based models leveragi…
cs.LG2024
WaveGNN: Integrating Graph Neural Networks and Transformers for Decay-Aware Classification of Irregular Clinical Time-Series
Arash Hajisafi, Maria Despoina Siampou, Bita Azarijoo +2
Clinical time series are often irregularly sampled, with varying sensor frequencies, missing observations, and misaligned timestamps. Prior approaches typically address these irreg…
stat.ME2023
Wasserstein complexity penalization priors: a new class of penalizing complexity priors
David Bolin, Alexandre B. Simas, Zhen Xiong
Penalizing complexity (PC) priors provide a principled framework for reducing model complexity by penalizing the Kullback--Leibler Divergence (KLD) between a ``simple'' base model…