DepWiGNN: A depth-wise graph neural network for multi-hop spatial reasoning in text

Spatial reasoning in text plays a crucial role in various real-world applications. Existing approaches for spatial reasoning typically infer spatial relations from pure text, which overlook the gap between natural language and symbolic structures. Graph neural networks (GNNs) have showcased exceptio...

Full description

Saved in:
Bibliographic Details
Main Authors: LI, Shuaiyi, DENG, Yang, LAM, Wai
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9119
https://ink.library.smu.edu.sg/context/sis_research/article/10122/viewcontent/2023.findings_emnlp.428.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10122
record_format dspace
spelling sg-smu-ink.sis_research-101222024-08-01T14:37:50Z DepWiGNN: A depth-wise graph neural network for multi-hop spatial reasoning in text LI, Shuaiyi DENG, Yang LAM, Wai Spatial reasoning in text plays a crucial role in various real-world applications. Existing approaches for spatial reasoning typically infer spatial relations from pure text, which overlook the gap between natural language and symbolic structures. Graph neural networks (GNNs) have showcased exceptional proficiency in inducing and aggregating symbolic structures. However, classical GNNs face challenges in handling multi-hop spatial reasoning due to the over-smoothing issue, i.e., the performance decreases substantially as the number of graph layers increases. To cope with these challenges, we propose a novel Depth-Wise Graph Neural Network (DepWiGNN). Specifically, we design a novel node memory scheme and aggregate the information over the depth dimension instead of the breadth dimension of the graph, which empowers the ability to collect long dependencies without stacking multiple layers. Experimental results on two challenging multi-hop spatial reasoning datasets show that DepWiGNN outperforms existing spatial reasoning methods. The comparisons with the other three GNNs further demonstrate its superiority in capturing long dependency in the graph. 2023-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9119 info:doi/10.18653/v1/2023.findings-emnlp.428 https://ink.library.smu.edu.sg/context/sis_research/article/10122/viewcontent/2023.findings_emnlp.428.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
Graphics and Human Computer Interfaces
spellingShingle Databases and Information Systems
Graphics and Human Computer Interfaces
LI, Shuaiyi
DENG, Yang
LAM, Wai
DepWiGNN: A depth-wise graph neural network for multi-hop spatial reasoning in text
description Spatial reasoning in text plays a crucial role in various real-world applications. Existing approaches for spatial reasoning typically infer spatial relations from pure text, which overlook the gap between natural language and symbolic structures. Graph neural networks (GNNs) have showcased exceptional proficiency in inducing and aggregating symbolic structures. However, classical GNNs face challenges in handling multi-hop spatial reasoning due to the over-smoothing issue, i.e., the performance decreases substantially as the number of graph layers increases. To cope with these challenges, we propose a novel Depth-Wise Graph Neural Network (DepWiGNN). Specifically, we design a novel node memory scheme and aggregate the information over the depth dimension instead of the breadth dimension of the graph, which empowers the ability to collect long dependencies without stacking multiple layers. Experimental results on two challenging multi-hop spatial reasoning datasets show that DepWiGNN outperforms existing spatial reasoning methods. The comparisons with the other three GNNs further demonstrate its superiority in capturing long dependency in the graph.
format text
author LI, Shuaiyi
DENG, Yang
LAM, Wai
author_facet LI, Shuaiyi
DENG, Yang
LAM, Wai
author_sort LI, Shuaiyi
title DepWiGNN: A depth-wise graph neural network for multi-hop spatial reasoning in text
title_short DepWiGNN: A depth-wise graph neural network for multi-hop spatial reasoning in text
title_full DepWiGNN: A depth-wise graph neural network for multi-hop spatial reasoning in text
title_fullStr DepWiGNN: A depth-wise graph neural network for multi-hop spatial reasoning in text
title_full_unstemmed DepWiGNN: A depth-wise graph neural network for multi-hop spatial reasoning in text
title_sort depwignn: a depth-wise graph neural network for multi-hop spatial reasoning in text
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/9119
https://ink.library.smu.edu.sg/context/sis_research/article/10122/viewcontent/2023.findings_emnlp.428.pdf
_version_ 1814047747316121600