Back to Search
Start Over
AG-Meta: Adaptive graph meta-learning via representation consistency over local subgraphs.
- Source :
-
Pattern Recognition . Jul2024, Vol. 151, pN.PAG-N.PAG. 1p. - Publication Year :
- 2024
-
Abstract
- Graph meta-learning has recently received significantly increased attention by virtue of its potential to extract common and transferable knowledge from learning different tasks on a graph. Existing methods for graph meta-learning usually leverage local subgraphs to transfer subgraph-specific information. However, they inherently face the challenge of imbalanced subgraphs due to inconsistent node density and different label distributions over local subgraphs. This paper proposes an adaptive graph meta-learning framework (AG-Meta) for learning the consistent and transferable representation of a graph in a way that can adapt to imbalanced subgraphs. Specifically, AG-Meta first learns the structural representation of subgraphs with various degrees using an Adaptive Graph Cascade Diffusion Network (AGCDN). AG-Meta then employs a prototype-consistency classifier to produce more accurate transferable inductive representations (also called prototypes) under few-shot settings with different label distributions of a subgraph. In the context of optimizing a model-agnostic meta-learner, a novel metric loss is finally introduced to achieve structural representation and prototype consistency. Extensive experiments are conducted to compare AG-Meta against baselines on five real-world networks, which validates that AG-Meta outperforms the state-of-the-art approaches. • A novel adaptive graph meta-learning framework is proposed. • An ensemble weight scheme is used to deal with inconsistency in densities and labels. • A prototypical-consistency loss is developed for graph meta-learning. • Our AG-Meta model outperforms several baselines. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 00313203
- Volume :
- 151
- Database :
- Academic Search Index
- Journal :
- Pattern Recognition
- Publication Type :
- Academic Journal
- Accession number :
- 176406943
- Full Text :
- https://doi.org/10.1016/j.patcog.2024.110387