Edge-case graphs show that permutation-invariant and cyclic-invariant quantum neural networks do not learn a simple edge-counting surrogate for graph connectedness.
Performance Evaluation in Machine Learning: The Good, the Bad, the Ugly, and the Way Forward,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
quant-ph 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Analysis of quantum neural network performance via edge cases
Edge-case graphs show that permutation-invariant and cyclic-invariant quantum neural networks do not learn a simple edge-counting surrogate for graph connectedness.