GNNs and HOMP models saturate an extended manifold triangulation benchmark when given appropriate representations but show no generalization beyond combinatorial structure, indicating a gap in topology-aware learning.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Graph invariants serve as expressive, task-agnostic baselines that characterize structural heterogeneity and match trained models across 26 datasets, indicating that expressivity is not the primary driver of performance.
citing papers explorer
-
No Triangulation Without Representation: Generalization in Topological Deep Learning
GNNs and HOMP models saturate an extended manifold triangulation benchmark when given appropriate representations but show no generalization beyond combinatorial structure, indicating a gap in topology-aware learning.
-
Invariant-Based Diagnostics for Graph Benchmarks
Graph invariants serve as expressive, task-agnostic baselines that characterize structural heterogeneity and match trained models across 26 datasets, indicating that expressivity is not the primary driver of performance.