works on
knowledge graph learning 1risk bounds 1supervised learning 1theoretical analysis 1unsupervised pretraining 1

From the 1 of 4 linked papers with an AI index.

collaborators
Showing math.STShow all

1 paper · 1 filter

math.ST2026

Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning

Jifan Zhang, Miklos Racz, Suqi Liu

The paper proposes a theoretically grounded two-stage framework that first unsupervisedly pretrains on heterogeneous data and then performs supervised learning for knowledge graph…