Search Results for author:
Found 5 papers, 2 papers with code
Is Rewiring Actually Helpful in Graph Neural Networks?
Graph neural networks compute node representations by performing multiple message-passing steps that consist in local aggregations of node features.
Addressing Heterophily in Node Classification with Graph Echo State Networks
Node classification tasks on graphs are addressed via fully-trained deep message-passing models that learn a hierarchy of node representations via multiple aggregations of a node's neighbourhood.
Ranked #1 on
Node Classification
on genius
(1:1 Accuracy metric)
Leave Graphs Alone: Addressing Over-Squashing without Rewiring
Recent works have investigated the role of graph bottlenecks in preventing long-range information propagation in message-passing graph neural networks, causing the so-called `over-squashing' phenomenon.
Beyond Homophily with Graph Echo State Networks
Graph Echo State Networks (GESN) have already demonstrated their efficacy and efficiency in graph classification tasks.
Ranked #5 on
Node Classification
on Pubmed Full-supervised
Dynamic Graph Echo State Networks
Dynamic temporal graphs represent evolving relations between entities, e. g. interactions between social network users or infection spreading.
