Graphs, recommendations, and time series · MLD-0862
Over-smoothing
A graph-network failure where repeated aggregation makes node representations insufficiently distinct.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Diagnose performance degradation in deep message-passing models.
Original caveat
Over-smoothing is distinct from ordinary overfitting.
Context and aliases
Level: Intermediate. Stages: Architecture · Data · Training · Inference.
Tags: ML · DL · Graph ML.
Aliases: None recorded.
Related concepts
Original references
- PyTorch Geometric documentation ↗ · Consulted
- scikit-learn User Guide ↗ · Consulted
- statsmodels: time series analysis ↗ · Reference link
- Original reference URL ↗