LATIDIA · Investigación

Degradado pero no del todo ineficaz: Redes neuronales de gráficos deformables basadas en PE

arXiv: 2609.13712v1Tipo de anuncio: nuevo Resumen: Muchos escenarios del mundo real se pueden representar utilizando datos estructurados por gráficos. Sin embargo, las GNN tradicionales que transmiten mensajes basados en vecinos de primer orden se han enfrentado durante mucho tiempo a

La noticia

arXiv:2609.13712v1 Announce Type: new Abstract: Many real-world scenarios can be represented using graph-structured data. However, traditional GNNs that transmit messages based on first-order neighbors have long faced several fundamental contradictions: increasing depth leads to over-smoothing, long-range dependencies cause over-compression, fixed neighborhoods restrict the receptive field, and on heterophilous graphs, topological neighbors become a source of noise. Although many works have addressed these issues individually, few mechanisms can simultaneously alleviate all of these challenges. To address the aforementioned problems, we propose a Position Encoding-Based Deformable Spatial Aggregation Module (PEBDSAM) that solves them all in one step. Specifically, we utilize a deformable mechanism in the position space to identify relevant nodes to