Node Embeddings Act As The Information Interface For Graph Neural Networks Yet Their Empirical Impact Is Often Reported Under Mismatched Backbones Splits And Training Budgets This Paper Provides A Controlled Benchmark Of Embedding Choices For Graph Classification Comparing Classical Baselines With Quantumoriented Node Representations Under A Unified Pipeline We Evaluate Two Classical Baselines Alongside Quantumoriented Alternatives Including A Circuitdefined Variational Embedding And Quantuminspired Embeddings Computed Via Graph Operators And Linearalgebraic Constructions All Variants Are Trained And Tested With The Same Backbone Stratified Splits Identical Optimization And Early Stopping And Consistent Metrics Experiments On Five Different Tu Datasets And On Qm9 Converted To Classification Via Target Binning Show Clear Dataset Dependence Quantumoriented Embeddings Yield The Most Consistent Gains On Structuredriven Benchmarks While Social Graphs With Limited Node Attributes Remain Well Served By Classical Baselines The Study Highlights Practical Tradeoffs Between Inductive Bias Trainability And Stability Under A Fixed Training Budget And Offers A Reproducible Reference Point For Selecting Quantumoriented Embeddings In Graph Learning

1 mentions across 0 people