Search Results for author:
Found 12 papers, 5 papers with code
GRANOLA: Adaptive Normalization for Graph Neural Networks
In recent years, significant efforts have been made to refine the design of Graph Neural Network (GNN) layers, aiming to overcome diverse challenges, such as limited expressive power and oversmoothing.
Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
In the realm of Graph Neural Networks (GNNs), two exciting research directions have recently emerged: Subgraph GNNs and Graph Transformers.
Efficient Subgraph GNNs by Learning Effective Selection Policies
Subgraph GNNs are provably expressive neural architectures that learn graph representations from sets of subgraphs.
A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes
The task of inductive link prediction in (discrete) attributed multigraphs infers missing attributed links (relations) between nodes in new test multigraphs.
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.
Neural Algorithmic Reasoning with Causal Regularisation
We evaluate our method on the CLRS algorithmic reasoning benchmark, where we show up to 3$\times$ improvements on the OOD test data.
Causal Lifting and Link Prediction
Existing causal models for link prediction assume an underlying set of inherent node factors -- an innate characteristic defined at the node's birth -- that governs the causal evolution of links in the graph.
A Generalist Neural Algorithmic Learner
The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution.
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.
Size-Invariant Graph Representations for Graph Classification Extrapolations
In general, graph representation learning methods assume that the train and test data come from the same distribution.
On Single-environment Extrapolations in Graph Classification and Regression Tasks
Extrapolation in graph classification/regression remains an underexplored area of an otherwise rapidly developing field.
