Projects per year
Abstract
Learning unbiased node representations for imbalanced samples in the graph has become a more remarkable and important topic. For the graph, a significant challenge is that the topological properties of the nodes (e.g., locations, roles) are unbalanced (topology-imbalance), other than the number of training labeled nodes (quantity-imbalance). Existing studies on topology-imbalance focus on the location or the local neighborhood structure of nodes, ignoring the global underlying hierarchical properties of the graph, i.e., hierarchy. In the real-world scenario, the hierarchical structure of graph data reveals important topological properties of graphs and is relevant to a wide range of applications. We find that training labeled nodes with different hierarchical properties have a significant impact on the node classification tasks and confirm it in our experiments. It is well known that hyperbolic geometry has a unique advantage in representing the hierarchical structure of graphs. Therefore, we attempt to explore the hierarchy-imbalance issue for node classification of graph neural networks with a novelty perspective of hyperbolic geometry, including its characteristics and causes. Then, we propose a novel hyperbolic geometric hierarchy-imbalance learning framework, named HyperIMBA, to alleviate the hierarchy-imbalance issue caused by uneven hierarchy-levels and cross-hierarchy connectivity patterns of labeled nodes. Extensive experimental results demonstrate the superior effectiveness of HyperIMBA for hierarchy-imbalance node classification tasks.
| Original language | English |
|---|---|
| Title of host publication | The ACM Web Conference 2023 |
| Subtitle of host publication | proceedings of The World Wide Web Conference WWW 2023 |
| Place of Publication | New York |
| Publisher | Association for Computing Machinery |
| Pages | 460-468 |
| Number of pages | 9 |
| ISBN (Electronic) | 9781450394161 |
| DOIs | |
| Publication status | Published - 2023 |
| Event | 2023 World Wide Web Conference, WWW 2023 - Austin, United States Duration: 30 Apr 2023 → 4 May 2023 |
Conference
| Conference | 2023 World Wide Web Conference, WWW 2023 |
|---|---|
| Country/Territory | United States |
| City | Austin |
| Period | 30/04/23 → 4/05/23 |
Keywords
- Graph representation learning
- imbalance learning
- hyperbolic space
- node classifcation
Fingerprint
Dive into the research topics of 'Hyperbolic geometric graph representation learning for hierarchy-imbalance node classification'. Together they form a unique fingerprint.Projects
- 1 Finished
-
DP230100899: New Graph Mining Technologies to Enable Timely Exploration of Social Events
Wu, J. (Primary Chief Investigator) & Yang, J. (Chief Investigator)
1/01/23 → 31/12/25
Project: Research
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver