DYNAMO-GAT prunes GNN attention edges between highly correlated nodes to prevent oversmoothing, but its main theoretical lemma contradicts its goal and its accuracy claims exceed its own table.
Simplifying the Theory on Over-Smoothing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Graph convolutions have gained popularity due to their ability to efficiently operate on data with an irregular geometric structure. However, graph convolutions cause over-smoothing, which refers to representations becoming more similar with increased depth. However, many different definitions and intuitions currently coexist, leading to research efforts focusing on incompatible directions. This paper attempts to align these directions by showing that over-smoothing is merely a special case of power iteration. This greatly simplifies the existing theory on over-smoothing, making it more accessible. Based on the theory, we provide a novel comprehensive definition of rank collapse as a generalized form of over-smoothing and introduce the rank-one distance as a corresponding metric. Our empirical evaluation of 14 commonly used methods shows that more models than were previously known suffer from this issue.
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks
DYNAMO-GAT prunes GNN attention edges between highly correlated nodes to prevent oversmoothing, but its main theoretical lemma contradicts its goal and its accuracy claims exceed its own table.