gHAWK: Local and Global Structure Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphs
cs.LG, cs.DB
Submitted: 2025-12-09
Updated: 2026-11-07
Code: https://github.com/lids-lab/gHAWK3https:
Terminology
Sources
- Layer Normalization
- Fast Graph Representation Learning with PyTorch Geometric
- OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Efficient Estimation of Word Representations in Vector Space
- KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
- eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis