Research map / Label-efficient and robust learning / Recognition and long-tail
Combining LLM Semantic Reasoning with GNN Structural Modeling for Multi-View Multi-Label Feature Selection
Zhiqi Chen, Yuzhou Liu, Jiarui Liu, Wanfu Gao
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| add LLM semantic graph to statistical graph (ablation) | GAT feature selector · SCENE | AP: 0.2842 -> 0.2888 | Improved |
| add LLM semantic graph to statistical graph (ablation) | GAT feature selector · Yeast | AP: 0.3025 -> 0.3398 | Improved |
| add LLM semantic graph to statistical graph (ablation) | GAT feature selector · Yeast | AUC: 0.5628 -> 0.5574 | Hurt |
| add LLM semantic graph to statistical graph (ablation) | GAT feature selector · Yeast | LRAP: 0.6625 -> 0.6583 | Hurt |
| add LLM semantic graph to statistical graph (ablation) | GAT feature selector · 3Sources | LRAP | Improved |
| swap Deepseek R1-14B for GPT-4o-mini as semantic scorer (ablation) | semantic scoring · SCENE | AP: 0.2875 -> 0.2888 | Improved |
| swap Deepseek R1-14B for GPT-4o-mini as semantic scorer (ablation) | semantic scoring · Yeast | AP: 0.3425 -> 0.3398 | Hurt |
| use full data instead of 50% for statistical graph (ablation) | semantic-heavy variant · SCENE | AP: 0.2310 -> 0.2888 | Improved |
| use full data instead of 50% for statistical graph (ablation) | semantic-heavy variant · Yeast | AP: 0.3001 -> 0.3398 | Improved |
| replace EF2FS with proposed method | EF2FS · SCENE | AP: 0.2499 -> 0.2888 | Improved |
| replace STFS with proposed method | STFS · VOC07 | AP: 0.1358 -> 0.1801 | Improved |
| replace ENM with proposed method | ENM · Yeast | LRAP: 0.6694 -> 0.6583 | Hurt |
Closest papers by meaning
- Label-free Node Classification on Graphs with Large Language Models (LLMs) (ICLR 2024 · similarity 0.90)
- Multi-View Multi-Label Classification via View-Label Matching Selection (AAAI 2025 · similarity 0.89)
- 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)
- Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs (AAAI 2025 · similarity 0.87)
- Multi-Label Node Classification with Label Influence Propagation (ICLR 2025 · similarity 0.86)
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.
