
The author proposes a Teacher-Free Graph Self-Distillation framework that eliminates the need for teachers or GNNs, achieving high accuracy and efficiency in graph inference.


coremsg

teacher-free-graph-knowledge-distillation-framework-with-dual-self-distillation


Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation


title_rewrite


FlyKD introduces a novel approach to generate unlimited pseudo labels on the fly, improving optimization over noisy pseudo labels through Curriculum Learning.


flykd-graph-knowledge-distillation-on-the-fly-with-curriculum-learning


FlyKD: Graph Knowledge Distillation on the Fly with Curriculum Learning



FlyKD enables unlimited pseudo label generation with Curriculum Learning for improved optimization over noisy labels.
