Melanie Weber
Melanie Weber
Home
Publications
Projects
Talks
Teaching
Contact
Light
Dark
Automatic
1
Higher-Order Learning with Graph Neural Networks via Hypergraph Encodings
Higher-order information is crucial for relational learning in many domains where relationships extend beyond pairwise interactions. …
R. Pellegrin
,
L. Fesser
,
M. Weber
PDF
Code
Project
Shared Global and Local Geometry of Language Model Embeddings
Researchers have recently suggested that models share common representations. In this work, we find that the token embeddings of …
A. Lee
,
M. Weber
,
F. Viegas
,
M. Wattenberg
PDF
Project
Neural Feature Geometry Evolves as Discrete Ricci Flow
Deep neural networks learn feature representations via complex geometric transformations of the input data manifold. Despite the …
M. Hehl
,
M.-K. von Renesse
,
M. Weber
PDF
Project
Position: Beyond Euclidean - Foundation Models Should Embrace Non-Euclidean Geometries
In the era of foundation models and Large Language Models (LLMs), Euclidean space has been the de facto geometric setting for machine …
N. He
,
J. Liu
,
B. Zhang
,
N. Bui
,
A. Maatouk
,
M. Yang
,
I. King
,
M. Weber
,
R. Ying
PDF
Project
Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups
The quest for robust and generalizable machine learning models has driven recent interest in exploiting symmetries through equivariant …
Z. Shumaylov
,
P. Zaika
,
J. Rowbottom
,
F. Sherry
,
M. Weber
,
C.-B. Schönlieb
PDF
Project
Performance Heterogeneity in Graph Neural Networks: Lessons for Architecture Design and Preprocessing
Graph Neural Networks have emerged as the most popular architecture for graph-level learning, including graph classification and …
L. Fesser
,
M. Weber
PDF
Project
Unitary convolutions for learning on graphs and groups
Group-convolutional architectures, which encode symmetries as inductive bias, have shown great success in applications, but can suffer …
B. T. Kiani
,
L. Fesser
,
M. Weber
PDF
Project
Hardness of Learning Neural Networks under the Manifold Hypothesis
The manifold hypothesis presumes that high-dimensional data lies on or near a low-dimensional manifold. While the utility of encoding …
B. T. Kiani
,
J. Wang
,
M. Weber
PDF
Project
Effective Structural Encodings via Local Curvature Profiles
Structural and Positional Encodings can significantly improve the performance of Graph Neural Networks in downstream tasks. Recent …
L. Fesser
,
M. Weber
PDF
Project
On the Hardness of Learning under Symmetries
We study the problem of learning equivariant neural networks via gradient descent. A recent line of learning theoretic research has …
B. T. Kiani
,
T. Le
,
H. Lawrence
,
S. Jegelka
,
M. Weber
PDF
Project
»
Cite
×