Publications

Preprints

On the Role of Attention Masks and LayerNorm in Transformers

Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs

What Are We Optimizing For? A Human-centric Evaluation of Deep Learning-based Movie Recommenders

Demystifying Oversmoothing in Attention-Based Graph Neural Networks

NeurIPS 2023 (Spotlight) / Paper

An Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks

ICLR 2023 / Paper

Link Partitioning on Simplicial Complexes Using Higher-Order Laplacians

ICDM 2022 / Paper / Code

Spectra of Quantum Graphs via a Scattering Matrix Approach

Xinyi Wu

Senior Thesis / Paper