Research map / Graph learning / Graph self-supervised learning
Learning on Large-scale Text-attributed Graphs via Variational Inference
Jianan Zhao, Meng Qu, Chaozhuo Li, Hao Yan, Qian Liu, Rui Li, Xing Xie, Jian Tang
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use GLEM-GNN instead of RevGAT with GIANT features | RevGAT on ogbn-arxiv · ogbn-arxiv test | accuracy: 75.90 ± 0.19 -> 76.97 ± 0.19 | Improved |
| Use GLEM-LM instead of fine-tuning the LM alone | DeBERTa on ogbn-arxiv · ogbn-arxiv test | accuracy: 74.13 ± 0.04 -> 75.71 ± 0.24 | Improved |
| Use GLEM-GNN instead of SAGN+ with GIANT features | SAGN+ on ogbn-products · ogbn-products test | accuracy: 86.67 ± 0.09 -> 87.36 ± 0.07 | Improved |
| Use GLEM-LM instead of fine-tuning the LM alone | DeBERTa on ogbn-products · ogbn-products test | accuracy: 79.63 ± 0.12 -> 84.83 ± 0.04 | Improved |
| Use GLEM-GNN instead of GAMLP+ with GIANT features | GAMLP+ on ogbn-papers100M · ogbn-papers100M test | accuracy: 69.67 ± 0.05 -> 70.36 ± 0.02 | Improved |
| Use GLEM-LM instead of fine-tuning the LM alone | DeBERTa on ogbn-papers100M · ogbn-papers100M test | accuracy: 63.52 ± 0.06 -> 66.71 ± 0.25 | Improved |
| Add GNN pseudo-label guidance to LM training instead of using gold labels only (α=0) (ablation) | GLEM-LM on ogbn-arxiv · ogbn-arxiv | accuracy | Improved |
| Vary the GNN pseudo-label weight (ablation) | GLEM-GNN on ogbn-arxiv · ogbn-arxiv | accuracy | No clear effect |
Closest papers by meaning
- Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models (ICML 2025 · similarity 0.92)
- Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning (ICLR 2024 · similarity 0.87)
- SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs (NeurIPS 2025 · similarity 0.87)
- Multi-View Empowered Structural Graph Wordification for Language Models (AAAI 2025 · similarity 0.87)
- Label-free Node Classification on Graphs with Large Language Models (LLMs) (ICLR 2024 · similarity 0.87)
- Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
