Search Results for author:
Found 3 papers, 1 papers with code
CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph
To estimate the DE, since the DE are generated through two paths (grab the attention assigned to neighbors and reduce the self-attention of the central node), we use Total Effect to model DE, which is a kind of causal estimand and can be estimated from intervened data; To weaken the DE, we identify the neighbors with the highest DE (we call them Distraction Neighbors) and remove them.
Ranked #1 on
Node Classification
on Cornell
Alleviating neighbor bias: augmenting graph self-supervise learning with structural equivalent positive samples
Then we compute the structural equivalence of node pairs based on their topological features.
STGC-GNNs: A GNN-based traffic prediction framework with a spatial-temporal Granger causality graph
We further propose spatial-temporal Granger causality (STGC) to express TCR, which models global and dynamic spatial dependence.
