Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
Oversmoothing in graph neural networks can be effectively tackled by a new index-theoretic criterion that reveals the true discriminative power of sheaf configurations.
SPD-SheafNets learn richer geometric representations than standard GNNs by operating directly on matrix-valued features, achieving SOTA on molecular property prediction by capturing relationships between directions.
