Do Higher-Order Models Win for Higher-Order Reasons? Rethinking Performance Gains in Hypergraph Learning
Higher-order models (e.g., hypergraph neural networks) often outperform lower-order baselines on hypergraph learning benchmarks, and their advantages are commonly attributed to their ability to exploit higher-order information.
ProofPaper ↗
Key points
- We therefore ask: Do higher-order models win for higher-order reasons?
- To investigate this question, we introduce a controlled performance-attribution framework that perturbs higher-order information while preserving the lower-order, i.e., pairwise, information.
- Across 25 commonly used hypergraph learning benchmarks spanning three tasks, we frequently observe an intriguing pattern: higher-order models originally outperform lower-order baselines, yet retain most of their advantage after perturbation.
- We find that simple additions to a lower-order baseline, e.g., richer pairwise weighting, more steps of pairwise feature propagation, and normalization, reduce the remaining performance gaps, supporting lower-order explanations for part of the observed advantage.
Sources (1)
- [1]Do Higher-Order Models Win for Higher-Order Reasons? Rethinking Performance Gains in Hypergraph LearningarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 08:44 AM
Higher-order models (e.g., hypergraph neural networks) often outperform lower-order baselines on hypergraph learning benchmarks, and their advantages are commonly attributed to their ability to exploit higher-order information.
We therefore ask: Do higher-order models win for higher-order reasons?
Extractive summary: sentences quoted from the sources.
