Search Results for author:
Found 15 papers, 11 papers with code
Topological Blind Spots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
Given the significant expressivity limitations of MPNNs, our paper aims to explore both the strengths and weaknesses of HOMP's expressive power and subsequently design novel architectures to address these limitations.
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
The product between the coarsened and the original graph reveals an implicit structure whereby subgraphs are associated with specific sets of nodes.
Future Directions in the Theory of Graph Machine Learning
Machine learning on graphs, especially using graph neural networks (GNNs), has seen a surge in interest due to the wide availability of graph data across a broad spectrum of disciplines, from life to social and engineering sciences.
Edge Directionality Improves Learning on Heterophilic Graphs
Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data.
Ranked #1 on
Node Classification on Non-Homophilic (Heterophilic) Graphs
on Chameleon (48%/32%/20% fixed splits)
Graph Neural Network
Node Classification on Non-Homophilic (Heterophilic) Graphs
Graph Positional Encoding via Random Feature Propagation
Two main families of node feature augmentation schemes have been explored for enhancing GNNs: random features and spectral positional encoding.
Graph Neural Networks for Link Prediction with Subgraph Sketching
Our experiments show that BUDDY also outperforms SGNNs on standard LP benchmarks while being highly scalable and faster than ELPH.
Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
Subgraph GNNs are a recent class of expressive Graph Neural Networks (GNNs) which model graphs as collections of subgraphs.
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.
Weisfeiler and Lehman Go Cellular: CW Networks
Nevertheless, these models can be severely constrained by the rigid combinatorial structure of Simplicial Complexes (SCs).
Ranked #1 on
Graph Regression
on ZINC 100k
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems.
Temporal Graph Networks for Deep Learning on Dynamic Graphs
Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social networks and recommendation systems.
Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
It has been shown that the expressive power of standard GNNs is bounded by the Weisfeiler-Leman (WL) graph isomorphism test, from which they inherit proven limitations such as the inability to detect and count graph substructures.
Ranked #2 on
Graph Regression
on ZINC 100k
SIGN: Scalable Inception Graph Neural Networks
Graph representation learning has recently been applied to a broad spectrum of problems ranging from computer graphics and chemistry to high energy physics and social media.
Ranked #5 on
Node Classification
on AMZ Comp
Learning Interpretable Disease Self-Representations for Drug Repositioning
Here, we propose an interpretable model that learns disease self-representations for drug repositioning.
Fake News Detection on Social Media using Geometric Deep Learning
One of the main reasons is that often the interpretation of the news requires the knowledge of political or social context or 'common sense', which current NLP algorithms are still missing.
