# Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs

arXiv: https://arxiv.org/abs/1910.00084 · HTML: https://mlsanity.com/paper/1910.00084/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

## Built on by (most cited first, 8 of 8)

- [On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence](https://mlsanity.com/paper/2304.06798/) (2023)
- [A Review of Location Encoding for GeoAI: Methods and Applications](https://mlsanity.com/paper/2111.04006/) (2021)
- [Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases](https://mlsanity.com/paper/2303.14617/) (2023)
- [AGI for Agriculture](https://mlsanity.com/paper/2304.06136/) (2023)
- [Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes](https://mlsanity.com/paper/2111.06854/) (2021)
- [Narrative Cartography with Knowledge Graphs](https://mlsanity.com/paper/2112.00970/) (2021)
- [Multimodal Cultural Heritage Knowledge Graph Extension with Language and Vision Models](https://mlsanity.com/paper/2605.17669/) (2026)
- [MissDiag: Diagnostic Evaluation of Incomplete-Knowledge Robustness in KGQA and KG-RAG](https://mlsanity.com/paper/2608.18489/) (2026)

## Abstract (arXiv)

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.