EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Knowledge Graph Multi-Hop Question Answering Method Based on Adaptive Graph Convolutional Neural Networks

Cheng Gan, Yuhang Cai, Shenyi Qian, Songhe Jin, Bowen Fu, Tongxin Zhao, Daiyi Li

Symmetry · 17.06.2026 · 18 (6) · 1048

DOI: 10.3390/sym18061048 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 17.06.2026. Verfasst von Cheng Gan und 6 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Research Project of Henan Province, Key Research and Development Special Project of Henan Provincial, China, Key Scientific Research Projects of Higher Education in Henan Province, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-hop question answering (MQA) requires models to perform multi-step reasoning and integrate multiple knowledge sources. However, existing methods combining pre-trained language models (PLMs) and graph neural networks (GNNs) often suffer from low computational efficiency, insufficient deep semantic fusion, and imbalanced modeling of heterogeneous relations. To solve these problems, we propose a Dynamic Hierarchical Adaptive Graph Convolution Network (DHACNet). First, to deal with the issues of insufficient computational efficiency and feature interpretability, we introduce Dynamic Sparse Activation (DSA). A trainable gate unit is used to generate importance masks for the encoder outputs, keeping only the task-relevant neurons. This greatly decreases the computational burden and enhances the interpretability of the model’s decisions. Second, to alleviate insufficient deep semantic fusion, we design a Hierarchical Feature Fusion (HFF) mechanism. It adaptively weights and fuses hidden states from different layers, enhancing the extraction and representation of deep textual semantics. Furthermore, for graph structure modeling, we present Adaptive Graph Convolution (AGC), which assigns learnable weights to different edge types in the graph, thereby improving heterogeneous relation modeling. Finally, hierarchical graph pooling is introduced, which integrates attention mechanism and Top-K selection to achieve efficient and robust graph-level representation. The experimental results show that our proposed model maintains the symmetry between the text representation and graph representation through adaptive layered fusion and relational perceptual graph propagation. This symmetry-aware reasoning process encourages semantic consistency during multi-hop inference and makes knowledge integration more robust.

Förderung

  • Science and Technology Research Project of Henan Province
  • Key Research and Development Special Project of Henan Provincial, China
  • Key Scientific Research Projects of Higher Education in Henan Province, China

Zitieren

APA

Gan, C., Cai, Y., Qian, S., Jin, S., Fu, B., Zhao, T., & Li, D. (2026). A Knowledge Graph Multi-Hop Question Answering Method Based on Adaptive Graph Convolutional Neural Networks. Symmetry, 18(6), 1048. https://doi.org/10.3390/sym18061048

Vancouver

Gan C, Cai Y, Qian S, Jin S, Fu B, Zhao T, et al. A Knowledge Graph Multi-Hop Question Answering Method Based on Adaptive Graph Convolutional Neural Networks. Symmetry. 2026;18(6):1048. doi:10.3390/sym18061048

BibTeX
@article{Gan2026,
  author = {Gan, Cheng and Cai, Yuhang and Qian, Shenyi and Jin, Songhe and Fu, Bowen and Zhao, Tongxin and Li, Daiyi},
  title = {A Knowledge Graph Multi-Hop Question Answering Method Based on Adaptive Graph Convolutional Neural Networks},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {6},
  pages = {1048},
  doi = {10.3390/sym18061048}
}
Kostenlos starten →