Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework

arXiv:2403.01079 · cs.LG, cs.AI · Submitted 2024-03-02 · Read on arXiv

cs.LG, cs.AI

Submitted: 2024-03-02

Updated: 2026-10-11

Comments: 20 pages, with Appendix

Code: https://github.com/lijunxian111/KMP

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 3× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Knowledge Distillation — 1× in this paper · explained in 12 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Semi-Supervised Classification with Graph Convolutional Networks
• A Comprehensive Survey on Graph Neural Networks
• Survey on Graph Neural Network Acceleration: An Algorithmic Perspective
• Accelerating Large Scale Real-Time GNN Inference using Channel Pruning
• Graph-based Knowledge Distillation by Multi-head Attention Network
• Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
• Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks
• FitNets: Hints for Thin Deep Nets
• How Powerful are Graph Neural Networks?
• DeeperGCN: All You Need to Train Deeper GCNs
• SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP
• Graph-MLP: Node Classification without Message Passing in Graph
• Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks
• On Self-Distilling Graph Neural Network
• Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
• Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning
• Distilling the Knowledge in a Neural Network

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks