Search Results for author:
Found 10 papers, 9 papers with code
Sign and Basis Invariant Networks for Spectral Graph Representation Learning
They are also theoretically strong for graph representation learning -- they can approximate any spectral graph convolution, can compute spectral invariants that go beyond message passing neural networks, and can provably simulate previously proposed graph positional encodings.
Ranked #2 on
Graph Regression
on ZINC-500k
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other.
Equivariant Subgraph Aggregation Networks
Thus, we propose to represent each graph as a set of subgraphs derived by some predefined policy, and to process it using a suitable equivariant architecture.
Equivariant Manifold Flows
Tractably modelling distributions over manifolds has long been an important goal in the natural sciences.
New Benchmarks for Learning on Non-Homophilous Graphs
Much data with graph structures satisfy the principle of homophily, meaning that connected nodes tend to be similar with respect to a specific attribute.
Ranked #1 on
Node Classification
on Yelp-Fraud
Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results
While message passing Graph Neural Networks (GNNs) have become increasingly popular architectures for learning with graphs, recent works have revealed important shortcomings in their expressive power.
Doubly Stochastic Subspace Clustering
Many state-of-the-art subspace clustering methods follow a two-step process by first constructing an affinity matrix between data points and then applying spectral clustering to this affinity.
Ranked #1 on
Image Clustering
on coil-40
Neural Manifold Ordinary Differential Equations
To better conform to data geometry, recent deep generative modelling techniques adapt Euclidean constructions to non-Euclidean spaces.
Expertise and Dynamics within Crowdsourced Musical Knowledge Curation: A Case Study of the Genius Platform
For example, expertise on song annotations follows a "U shape" where experts are both early and late contributors with non-experts contributing intermediately; we develop a user utility model that captures such behavior.
The Doubly Stochastic Single Eigenvalue Problem: A Computational Approach
The problem of determining $DS_n$, the complex numbers that occur as an eigenvalue of an $n$-by-$n$ doubly stochastic matrix, has been a target of study for some time.
Spectral Theory 15-04, 15A18, 15A29, 15B51
