Showing eess.SPShow all
3 papers · 1 filter
eess.SP2025
GegenbauerNet: Finding the Optimal Compromise in the GNN Flexibility-Stability Trade-off
Huseyin Goksu
Spectral Graph Neural Networks (GNNs) operating in the canonical [-1, 1] domain (like ChebyNet and its adaptive generalization, L-JacobiNet) face a fundamental Flexibility-Stabilit…
eess.SP2025
DualLaguerreNet: A Decoupled Spectral Filter GNN and the Uncovering of the Flexibility-Stability Trade-off
Huseyin Goksu
Graph Neural Networks (GNNs) based on spectral filters, such as the Adaptive Orthogonal Polynomial Filter (AOPF) class (e.g., LaguerreNet), have shown promise in unifying the solut…
eess.SP2025
Hi-WaveTST: A Hybrid High-Frequency Wavelet-Transformer for Time-Series Classification
Huseyin Goksu
Transformers have become state-of-the-art (SOTA) for time-series classification, with models like PatchTST demonstrating exceptional performance. These models rely on patching the…