A polarity-aware hypergraph GNN framework improves unsat core prediction in SAT by separating polarity-invariant and equivariant literal representations.
Proceedings of the AAAI Conference on Artificial Intelligence , author=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
GHI introduces an incidence-based structural reasoning layer using Graphormer on conditioned hypergraphs for ABSA, reporting outperformance on SemEval benchmarks, near-parity with 11B models at 247M parameters, and robustness on ARTS.
A new hierarchical splitting scheme recovers random 3-uniform hypergraphs with O(m log n) queries and O(m^{5/3} log n) decoding time for θ > 2/3.
citing papers explorer
-
Unsat Core Prediction through Polarity-Aware Representation Learning over Clause-Literal Hypergraphs
A polarity-aware hypergraph GNN framework improves unsat core prediction in SAT by separating polarity-invariant and equivariant literal representations.
-
GHI: Graphormer over Conditioned Hypergraph Incidence for Aspect-Based Sentiment Analysis
GHI introduces an incidence-based structural reasoning layer using Graphormer on conditioned hypergraphs for ABSA, reporting outperformance on SemEval benchmarks, near-parity with 11B models at 247M parameters, and robustness on ARTS.
-
A Fast Hierarchical Splitting Approach for Non-Adaptive Learning of Random Hypergraphs
A new hierarchical splitting scheme recovers random 3-uniform hypergraphs with O(m log n) queries and O(m^{5/3} log n) decoding time for θ > 2/3.