Hierarchical Graph Capsule Network
Not on the map. Why?
Abstract (arXiv)
Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data. However, existing GNNs suffer from limited capability in capturing the hierarchical graph representation which plays an important role in graph classification. In this paper, we innovatively propose hierarchical graph capsule network (HGCN) that can jointly learn node embeddings and extract graph hierarchies. Specifically, disentangled graph capsules are established by identifying heterogeneous factors underlying each node, such that their instantiation parameters represent different properties of the same entity. To learn the hierarchical representation, HGCN characterizes the part-whole relationship between lower-level capsules (part) and higher-level capsules (whole) by explicitly considering the structure information among the parts. Experimental studies demonstrate the effectiveness of HGCN and the contribution of each component.
Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Dec 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 4; 2023: 3; 2024: 2; 2025: 1.
11 papers.
- 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
- 2021Distribution Knowledge Embedding for Graph Poolingcited by 19
- 2023Dynamic Hypergraph Structure Learning for Traffic Flow Forecastingcited by 14
- 2023Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attentioncited by 12
- 2023Topological Pooling on Graphscited by 9
- 2022Hierarchical Capsule Prediction Network for Marketing Campaigns Effectcited by 5
- 2022Incorporating Heterophily into Graph Neural Networks for Graph Classificationcited by 4
- 2024Capsule Network Projectors are Equivariant and Invariant Learnerscited by 2
- 2024Relaxing Continuous Constraints of Equivariant Graph Neural Networks for Physical Dynamics Learningcited by 1
- 2022GPN: A Joint Structural Learning Framework for Graph Neural Networkscited by 0
- 2025Reducing Smoothness with Expressive Memory Enhanced Hierarchical Graph Neural Networkscited by 0
- 2025Reducing Smoothness with Expressive Memory Enhanced Hierarchical Graph Neural Networks1 Apr 2025
- 2024Relaxing Continuous Constraints of Equivariant Graph Neural Networks for Physical Dynamics Learning24 Jun 2024
- 2024Capsule Network Projectors are Equivariant and Invariant Learners23 May 2024
- 2023Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting21 Sep 2023
- 2023Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention6 Apr 2023
- 2023Topological Pooling on Graphs25 Mar 2023
- 2022Hierarchical Capsule Prediction Network for Marketing Campaigns Effect22 Aug 2022
- 2022GPN: A Joint Structural Learning Framework for Graph Neural Networks12 May 2022
- 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities15 Apr 2022
- 2022Incorporating Heterophily into Graph Neural Networks for Graph Classification15 Mar 2022
- 2021Distribution Knowledge Embedding for Graph Pooling29 Sep 2021