首页 > AI前沿 > Learning Graph-Conditioned Predictors in Weight Space

Learning Graph-Conditioned Predictors in Weight Space

arXiv机器学习 2026-11-14 16:23 23 阅读 查看原文

The same node attributes can imply different labels in different structural contexts. Yet fast graphless models typically treat topology as additional evidence supplied to a globally shared predictor. This assumes that structure augments the available information, rather than determining how node attributes should be interpreted.

We introduce SCOPE (Structure-COnditioned PrEdictor), in which a small generator maps each node's cached structural fingerprint to coefficients over a shared low-rank basis, producing a context-specific update to a global weight matrix. The base predictor, basis, and generator remain shared across all nodes, while the resulting transformation adapts how attributes are processed in each relational environment