Research map / Vision-language and multimodal / Cross-modal learning
MyGram: Modality-aware Graph Transformer with Global Distribution for Multi-modal Entity Alignment
Zhifei Li, Ziyue Qin, Xiangyu Luo, Xiaoju Hou, Yue Zhao, Miao Zhang, Zhifang Huang, Kui Xiao, Bing Yang
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 relation modality (ablation) | MyGram · FB15K-DB15K (80% seed) | Hits@1: .822 -> .842 | Improved |
| add relation modality (ablation) | MyGram · FB15K-YG15K (80% seed) | Hits@1: .761 -> .783 | Improved |
| add attribute modality (ablation) | MyGram · FB15K-DB15K (80% seed) | Hits@1: .834 -> .842 | Improved |
| add attribute modality (ablation) | MyGram · FB15K-YG15K (80% seed) | Hits@1: .768 -> .783 | Improved |
| add image modality (ablation) | MyGram · FB15K-DB15K (80% seed) | Hits@1: .829 -> .842 | Improved |
| add image modality (ablation) | MyGram · FB15K-YG15K (80% seed) | Hits@1: .772 -> .783 | Improved |
| add modality-aware graph convolutional diffusion (MGD) (ablation) | MyGram · FB15K-DB15K and FB15K-YG15K | Hits@1 | Improved |
| add Gram loss (ablation) | MyGram · FB15K-DB15K and FB15K-YG15K | Hits@1 | Improved |
| MyGram vs SimDiff at 80% seed | MyGram · FB15K-DB15K (80% seed) | Hits@1: .829 -> .842 | Improved |
| MyGram vs IBMEA at 20% seed | MyGram · FB15K-YG15K (20% seed) | Hits@1: .521 -> .629 | Improved |
Closest papers by meaning
- Tackling Uncertain Correspondences for Multi-Modal Entity Alignment (NeurIPS 2024 · similarity 0.92)
- Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation (AAAI 2025 · similarity 0.89)
- Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning (ICLR 2025 · similarity 0.89)
- Pseudo-Label Calibration Semi-supervised Multi-Modal Entity Alignment (AAAI 2024 · similarity 0.88)
- Beyond Entities: A Large-Scale Multi-Modal Knowledge Graph with Triplet Fact Grounding (AAAI 2024 · similarity 0.87)
- MESED: A Multi-Modal Entity Set Expansion Dataset with Fine-Grained Semantic Classes and Hard Negative Entities (AAAI 2024 · 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.
