Research map / Graph learning / Graph self-supervised learning
Modular Graph Transformer Networks for Multi-Label Image Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 MGTN with eigenvector-based embedding transformation instead of MGTN(BASE) (ablation) | MGTN · MS-COCO | mAP: 86.9 -> 87.0 | Helped |
| Use modular graph transformer networks instead of SGTN | MS-COCO · MS-COCO | mAP: 0.4% | Helped |
| Use modular graph transformer networks instead of A-GCN | Fashion550K · Fashion550K | mAP: 3.7% | Helped |
| Use eigenvector-enhanced label embeddings (ablation) | MGTN with different tested label embeddings · MS-COCO | learning speed | Helped |
| Use different language models to extract label embeddings (ablation) | MGTN · MS-COCO | learning speed | Mixed |
| Average RoBERTa representations across 12 layers rather than using a few final layers (ablation) | MGTN label embeddings · MS-COCO | learning speed | Hurt |
Closest papers by meaning
- HGDL: Heterogeneous Graph Label Distribution Learning (NeurIPS 2024 · similarity 0.87)
- NLGT: Neighborhood-based and Label-enhanced Graph Transformer Framework for Node Classification (AAAI 2025 · similarity 0.86)
- Multi-Label Node Classification with Label Influence Propagation (ICLR 2025 · similarity 0.86)
- ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detection (AAAI 2025 · similarity 0.86)
- GLDL: Graph Label Distribution Learning (AAAI 2024 · similarity 0.85)
- Deep Multi-modal Graph Clustering via Graph Transformer Network (AAAI 2025 · similarity 0.85)
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.