Ningyuan Teresa Huang — accepted AI-conference papers

2025

CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning

Ningyuan Teresa Huang, Richard Stiskalek, Jun-Young Lee, Adrian E. Bayer, Charles Margossian, Christian Kragh Jespersen +3

NeurIPS 2025poster

Cosmological simulations provide a wealth of data in the form of point clouds and directed trees. A crucial goal is to extract insights from this data that shed light on the nature and composition of the Universe. In this paper we introduce CosmoBench, a benchmark dataset curated from state-of-the-a…

Cited by 0 Source ↗Scholar ↗

2025

Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity

Ningyuan Teresa Huang, Miguel Sarabia, Abhinav Moudgil, Pau Rodriguez, Luca Zappella, Federico Danieli

ICML 2025poster

State-Space Models (SSMs), and particularly Mamba, have recently emerged as a promising alternative to Transformers. Mamba introduces input selectivity to its SSM layer (S6) and incorporates convolution and gating into its block definition. While these modifications do improve Mamba's performance ov…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

A Spectral Analysis of Graph Neural Networks on Dense and Sparse Graphs

Luana Ruiz, Ningyuan Teresa Huang, Soledad Villar

ICASSP 2024accepted

In this work we propose a random graph model that can produce graphs at different levels of sparsity. We analyze how sparsity affects the graph spectra, and thus the performance of graph neural networks (GNNs) in node classification on dense and sparse graphs. We compare GNNs with spectral methods k…

Cited by 0 Source ↗Scholar ↗

2023

Approximately Equivariant Graph Networks

Ningyuan Teresa Huang, Ron Levie, Soledad Villar

NeurIPS 2023poster

Graph neural networks (GNNs) are commonly described as being permutation equivariant with respect to node relabeling in the graph. This symmetry of GNNs is often compared to the translation equivariance of Euclidean convolution neural networks (CNNs). However, these two symmetries are fundamentally…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗

2023

Fine-grained Expressivity of Graph Neural Networks

Jan Böker, Ron Levie, Ningyuan Teresa Huang, Soledad Villar, Christopher Morris

NeurIPS 2023poster

Numerous recent works have analyzed the expressive power of message-passing graph neural networks (MPNNs), primarily utilizing combinatorial techniques such as the $1$-dimensional Weisfeiler--Leman test ($1$-WL) for the graph isomorphism problem. However, the graph isomorphism objective is inherentl…

Cited by 34 Source ↗PDF ↗code ↗Scholar ↗

2021

A Short Tutorial on The Weisfeiler-Lehman Test And Its Variants

Ningyuan Teresa Huang, Soledad Villar

ICASSP 2021accepted

Graph neural networks are designed to learn functions on graphs. Typically, the relevant target functions are invariant with respect to actions by permutations. Therefore the design of some graph neural network architectures has been inspired by graph-isomorphism algorithms.The classical Weisfeiler-…

Cited by 0 Source ↗Scholar ↗