A new attention mechanism adds persistent homology and Euler-based topological structure to time-series models via validation-gated residuals, yielding RMSE reductions of 12.5-47.8% in paired tests on synthetic and real datasets when geometry is predictive.
Topology-informed graph transformer
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
S³GNN mitigates oversquashing in message-passing networks via lightweight global mixing without strong prior assumptions, yielding up to 10x error reduction and 50% fewer parameters across multiple domains.
citing papers explorer
-
Global and Local Topology-Aware Attention with Persistent Homology and Euler Biases for Time-Series Forecasting
A new attention mechanism adds persistent homology and Euler-based topological structure to time-series models via validation-gated residuals, yielding RMSE reductions of 12.5-47.8% in paired tests on synthetic and real datasets when geometry is predictive.
-
S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
S³GNN mitigates oversquashing in message-passing networks via lightweight global mixing without strong prior assumptions, yielding up to 10x error reduction and 50% fewer parameters across multiple domains.