# Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering

arXiv: https://arxiv.org/abs/2104.00218 · HTML: https://mlsanity.com/paper/2104.00218/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 1 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [Variational Reasoning for Question Answering with Knowledge Graph](https://mlsanity.com/paper/1709.04071/) (2017)
- [Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text](https://mlsanity.com/paper/1809.00782/) (2018)
- [Cognitive Graph for Multi-Hop Reading Comprehension at Scale](https://mlsanity.com/paper/1905.05460/) (2019)
- [An Interpretable Reasoning Network for Multi-Relation Question Answering](https://mlsanity.com/paper/1801.04726/) (2018)
- [Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader](https://mlsanity.com/paper/1905.07098/) (2019)

## Built on by (most cited first, 1 of 1)

- [LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning](https://mlsanity.com/paper/2406.15859/) (2024)

## Abstract (arXiv)

Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities. Although effective, most of these models solely rely on fixed relation representations to obtain answers for different question-related KB subgraphs. Hence, the rich structured information of these subgraphs may be overlooked by the relation representation vectors. Meanwhile, the direction information of reasoning, which has been proven effective for the answer prediction on graphs, has not been fully explored in existing work. To address these challenges, we propose a novel neural model, Relation-updated Direction-guided Answer Selector (RDAS), which converts relations in each subgraph to additional nodes to learn structure information. Additionally, we utilize direction information to enhance the reasoning ability. Experimental results show that our model yields substantial improvements on two widely used datasets.