Hypergraph neural networks obey a strict expressivity hierarchy indexed by hypertree width, creating a Width Wall that no fixed-depth model, hidden dimension, or training procedure can cross for wider patterns.
How powerful are graph neural networks? InInternational Conference on Learning Representations (ICLR), 2019
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
HGPM learns compositional patterns in hypergraphs by subset tokenization and inclusion-aware masked Transformer reconstruction, matching or exceeding SOTA on ten benchmarks and correctly identifying inhibitory drug additions in adverse-event prediction where prior methods fail.
COPYCOP identifies copycat GNNs by matching their node embeddings despite architectural differences and adversarial transformations, backed by theoretical guarantees and tests on 14 datasets across 5 architectures.
citing papers explorer
-
The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
Hypergraph neural networks obey a strict expressivity hierarchy indexed by hypertree width, creating a Width Wall that no fixed-depth model, hidden dimension, or training procedure can cross for wider patterns.
-
Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions
HGPM learns compositional patterns in hypergraphs by subset tokenization and inclusion-aware masked Transformer reconstruction, matching or exceeding SOTA on ten benchmarks and correctly identifying inhibitory drug additions in adverse-event prediction where prior methods fail.
-
COPYCOP: Ownership Verification for Graph Neural Networks
COPYCOP identifies copycat GNNs by matching their node embeddings despite architectural differences and adversarial transformations, backed by theoretical guarantees and tests on 14 datasets across 5 architectures.