Soledad Villar
9 papers · 2019–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (12) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Conference Polyglot
(4)
π
Academic Marathon
(5)
π
Cross-Pollinator
(12)
π
Triple Crown
β
The Questioner
(2)
Conferences
NIPS (6)
ICLR (1)
ICML (1)
JMLR (1)
Top co-authors
Keywords
graph neural network
(5)
message passing
(2)
graph isomorphism
(2)
group theory
(1)
stability analysis
(1)
machine learning
(1)
expressive power
(1)
image inpainting
(1)
equivariant learning
(1)
graph convolution
(1)
non-commuting operator
(1)
graphon theory
(1)
equivariant neural network
(1)
symbolic regression
(1)
permutation invariance
(1)
traffic flow prediction
(1)
physical law
(1)
prediction accuracy
(1)
dimensional analysis
(1)
equivariant machine learning
(1)
Papers
Position: Is machine learning good or bad for the natural sciences?
ICML 2024
Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning
ICLR 2024
Graph neural networks and non-commuting operators
NIPS 2024
Dimensionless machine learning: Imposing exact units equivariance
JMLR 2023
Approximately Equivariant Graph Networks
NIPS 2023
Fine-grained Expressivity of Graph Neural Networks
NIPS 2023
Scalars are universal: Equivariant machine learning, structured like classical physics
NIPS 2021
Can Graph Neural Networks Count Substructures?
NIPS 2020
On the equivalence between graph isomorphism testing and function approximation with GNNs
NIPS 2019