Search papers, labs, and topics across Lattice.
Berlin Institute for the Foundations of Learning and Data -BIFOLD, Technical University of Berlin
2
0
2
A new attribution method reveals the full spectrum of information flow in ETGNNs, enhancing explainability beyond traditional event-related embeddings.
Exponential complexity in GNN explainability is no longer a barrier: this work achieves linear-time subgraph attribution via message passing.
