Code for AAAI 2023 (Oral) paper "Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework"

Code for ICML 2023 paper "Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs"

Code for TKDE paper "A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation"

Code fo CIKM2024 paper "Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation"

MAGI: Markdown for Agent Guidance & Instruction - A next-generation markdown extension designed specifically for AI systems. MAGI enhances standard markdown with structured metadata, embedded AI instructions, and explicit document relationships, creating a seamless bridge between human-readable content and LLM/agent processing. Perfect for RAG,KAG