Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs
| Autor: | Ling Cai, Gengchen Mai, Krzysztof Janowicz, Rui Zhu, Ni Lao, Bo Yan |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Theoretical computer science Computer Science - Artificial Intelligence Computer science Machine Learning (stat.ML) 02 engineering and technology 010501 environmental sciences 01 natural sciences Machine Learning (cs.LG) Incomplete knowledge Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering Leverage (statistics) Multi-head attention model 0105 earth and related environmental sciences I.1.3 Computer Science - Computation and Language I.2.4 Logical query Center embedding Attention model Graph Artificial Intelligence (cs.AI) Knowledge graph embedding Embedding 020201 artificial intelligence & image processing Computation and Language (cs.CL) Logical query answering |
| Zdroj: | K-CAP Mai, G, Janowicz, K, Yan, B, Zhu, R, Cai, L & Lao, N 2019, Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs . in K-CAP 2019-Proceedings of the 10th International Conference on Knowledge Capture . K-CAP, Association for Computing Machinery (ACM), pp. 171-178, 10th International Conference on Knowledge Capture, K-CAP 2019, Marina Del Rey, United States, 19/11/19 . https://doi.org/10.1145/3360901.3364432, https://doi.org/10.1145/3360901.3364432 |
| DOI: | 10.1145/3360901.3364432 |
| Popis: | Recently, several studies have explored methods for using KG embedding to answer logical queries. These approaches either treat embedding learning and query answering as two separated learning tasks, or fail to deal with the variability of contributions from different query paths. We proposed to leverage a graph attention mechanism to handle the unequal contribution of different query paths. However, commonly used graph attention assumes that the center node embedding is provided, which is unavailable in this task since the center node is to be predicted. To solve this problem we propose a multi-head attention-based end-to-end logical query answering model, called Contextual Graph Attention model(CGA), which uses an initial neighborhood aggregation layer to generate the center embedding, and the whole model is trained jointly on the original KG structure as well as the sampled query-answer pairs. We also introduce two new datasets, DB18 and WikiGeo19, which are rather large in size compared to the existing datasets and contain many more relation types, and use them to evaluate the performance of the proposed model. Our result shows that the proposed CGA with fewer learnable parameters consistently outperforms the baseline models on both datasets as well as Bio dataset. Comment: 8 pages, 3 figures, camera ready version of article accepted to K-CAP 2019, Marina del Rey, California, United States |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|