Multimodal Knowledge Graph Completion via Relation-Aware Negative Sampling with Diffusion-Based Interpolation
Summary: RelDINS performs relation-cardinality-aware multimodal embedding learning and diffusion-space interpolation to generate hardness-tunable negative samples. It improves semantic consistency and achieves state-of-the-art MMKG completion accuracy. (summarized by gpt-5.6-luna on Aug 17 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Qian Ma (Dalian Maritime University)
- 2. Linfei Dai (Dalian Maritime University)
- 3. Zhongming Yao (Northeastern University)
- 4. Yu Gu (Northeastern University)
- 5. Tianyi Li (Aalborg University)
- 6. Christian S. Jensen (Aalborg University)
- 7. Ge Yu (Northeastern University)
BibTeX Citation
@article{ma_vldb26,
title = {{Multimodal Knowledge Graph Completion via Relation-Aware Negative Sampling with Diffusion-Based Interpolation}},
author = {Ma, Qian and Dai, Linfei and Yao, Zhongming and Gu, Yu and Li, Tianyi and Jensen, Christian S. and Yu, Ge},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {9},
pages = {1949--1962},
doi = {10.14778/3819518.3819526},
url = {https://doi.org/10.14778/3819518.3819526},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 4,548 | Explaining Link Prediction Systems based on Knowledge Graph Embeddings | 2022 | SIGMOD | 6.5423862e-05 |
| 5,310 | DynaHB: A Communication-Avoiding Asynchronous Distributed Framework with Hybrid Batches for Dynamic GNN Training | 2024 | VLDB | 6.1857447e-05 |
| 7,644 | eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules | 2025 | VLDB | 5.4772833e-05 |
| 7,645 | Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completion | 2025 | VLDB | 5.4772833e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,148 | A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs | 2020 | VLDB |
| 2 | 8,679 | Relational Deep Dive: Error-Aware Queries Over Unstructured Data | 2026 | VLDB |
| 3 | 3,208 | Relation Strength-Aware Clustering of Heterogeneous Information Networks with Incomplete Attributes | 2012 | VLDB |
| 4 | 4,995 | Medical Entity Disambiguation Using Graph Neural Networks | 2021 | SIGMOD |
| 5 | 8,282 | Online Topic-Aware Entity Resolution Over Incomplete Data Streams | 2021 | SIGMOD |
| 6 | 6,469 | Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks | 2024 | SIGMOD |
| 7 | 11,590 | Enriching Relations with Additional Attributes for ER | 2024 | VLDB |
| 8 | 2,795 | Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study | 2020 | SIGMOD |
| 9 | 13,579 | Effective Clustering for Large Multi-Relational Graphs | 2026 | SIGMOD |
| 10 | 1,391 | Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks | 2020 | SIGMOD |