38 citations · 82 across the 18 of their papers we have counts for
18 papers
Subzero matrix completion for sparse data analysis: large-scale learning of latent low-rank structure
Lawrence K. Saul, Ningyuan Huang, Dennis Bollweg +2
We investigate when a sparse nonnegative matrix can be recovered from a real-valued matrix of much lower rank by zeroing out its negative elements. The potential for such decomposi…
Attention to Mamba: A Recipe for Cross-Architecture Distillation
Abhinav Moudgil, Ningyuan Huang, Eeshan Gunesh Dhekane +3
State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher throughput at generation compare…
Any-Subgroup Equivariant Networks via Symmetry Breaking
Abhinav Goel, Derek Lim, Hannah Lawrence +2
The inclusion of symmetries as an inductive bias, known as equivariance, often improves generalization on geometric data (e.g. grids, sets, and graphs). However, equivariant archit…
World Guidance: World Modeling in Condition Space for Action Generation
Yue Su, Sijin Chen, Haixin Shi +7
Leveraging future observation modeling to facilitate action generation presents a promising avenue for enhancing the capabilities of Vision-Language-Action (VLA) models. However, e…
Multi-View Graph Learning with Graph-Tuple
Shiyu Chen, Ningyuan Huang, Soledad Villar
Graph Neural Networks (GNNs) typically scale with the number of graph edges, making them well suited for sparse graphs but less efficient on dense graphs, such as point clouds or m…
A Galois theorem for machine learning: Functions on symmetric matrices and point clouds via lightweight invariant features
Ben Blum-Smith, Ningyuan Huang, Marco Cuturi +1
In this work, we present a mathematical formulation for machine learning of (1) functions on symmetric matrices that are invariant with respect to the action of permutations by con…
Approximately Equivariant Graph Networks
Ningyuan Huang, Ron Levie, Soledad Villar
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 tr…
Fine-grained Expressivity of Graph Neural Networks
Jan Böker, Ron Levie, Ningyuan Huang +2
Numerous recent works have analyzed the expressive power of message-passing graph neural networks (MPNNs), primarily utilizing combinatorial techniques such as the -dimensional…
A Spectral Analysis of Graph Neural Networks on Dense and Sparse Graphs
Luana Ruiz, Ningyuan Huang, Soledad Villar
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…
Deep Learning is Provably Robust to Symmetric Label Noise
Carey E. Priebe, Ningyuan Huang, Soledad Villar +2
Deep neural networks (DNNs) are capable of perfectly fitting the training data, including memorizing noisy data. It is commonly believed that memorization hurts generalization. The…
From Local to Global: Spectral-Inspired Graph Neural Networks
Ningyuan Huang, Soledad Villar, Carey E. Priebe +4
Graph Neural Networks (GNNs) are powerful deep learning methods for Non-Euclidean data. Popular GNNs are message-passing algorithms (MPNNs) that aggregate and combine signals in a…
Endowing Language Models with Multimodal Knowledge Graph Representations
Ningyuan Huang, Yash R. Deshpande, Yibo Liu +4
We propose a method to make natural language understanding models more parameter efficient by storing knowledge in an external knowledge graph (KG) and retrieving from this KG usin…
Deep Learning with Label Noise: A Hierarchical Approach
Li Chen, Ningyuan Huang, Cong Mu +4
Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the net…
Prospective Learning: Principled Extrapolation to the Future
Ashwin De Silva, Rahul Ramesh, Lyle Ungar +40
Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the…
A Short Tutorial on The Weisfeiler-Lehman Test And Its Variants
Ningyuan Huang, Soledad Villar
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 desig…
Dimensionality reduction, regularization, and generalization in overparameterized regressions
Ningyuan Huang, David W. Hogg, Soledad Villar
Overparameterization in deep learning is powerful: Very large models fit the training data perfectly and yet often generalize well. This realization brought back the study of linea…
A Simple Spectral Failure Mode for Graph Convolutional Networks
Carey E. Priebe, Cencheng Shen, Ningyuan Huang +1
Neural networks have achieved remarkable successes in machine learning tasks. This has recently been extended to graph learning using neural networks. However, there is limited the…
VisualSem: A High-quality Knowledge Graph for Vision and Language
Houda Alberts, Teresa Huang, Yash Deshpande +4
An exciting frontier in natural language understanding (NLU) and generation (NLG) calls for (vision-and-) language models that can efficiently access external structured knowledge…