Tiantian He

Learning Conjoint Attentions for Graph Neural Nets

2021 · arXiv (Cornell University)

In this paper, we present Conjoint Attentions (CAs), a class of novel learning-to-attend strategies for graph neural networks (GNNs). Besides considering the layer-wise node features propagated within the GNN, CAs can additionally incorporate various structural …

Efficient polarization-insensitive quasi-BIC modulation by VO ₂ thin films

2024 · Optics Express

Bound states in the continuum (BIC) offer great design freedom for realizing high-quality factor metasurfaces. By deliberately disrupting the inherent symmetries, BIC can degenerate into quasi-BIC exhibiting sharp spectra with strong light confinement. This transformation …

Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated Learning

2024 · arXiv (Cornell University)

There is growing research interest in measuring the statistical heterogeneity of clients' local datasets. Such measurements are used to estimate the suitability for collaborative training of personalized federated learning (PFL) models. Currently, these research endeavors …