DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text

TL;DR

Experimental results on two challenging multi-hop spatial reasoning datasets show that DepWiGNN outperforms existing spatial reasoning methods, and comparisons with the other three GNNs further demonstrate its superiority in capturing long dependency in the graph.

Abstract

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 overlooks 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.

Figures (5)

• Figure 1: An example of multihop spatial reasoning in text from the StepGame dataset aaai22-stepgame.
• Figure 2: The DepWiNet framework. The entity representations are first extracted from the entity representation extraction module (left), and then a homogeneous graph is constructed based on the entity embeddings and fed into the DepWiNet reasoning module. The DepWiNet depth-wisely aggregates information for all indirectly connected node pairs, and stores it in node memories. The updated node embeddings are then passed to the prediction module.
• Figure 3: The illustration of DepWiGNN.
• Figure 4: Impact of the layer number in different GNNs on StepGame. The solid and dashed lines denote the mean score of ($k$=1-5) and ($k$=6-10) respectively.
• Figure 5: Cases with distracting noisy from StepGame.