Attentive Graph Neural Networks for Few-Shot Learning
This work addresses scalability issues in GNNs for few-shot learning, which is an incremental improvement in a domain-specific area.
The paper tackles the problems of over-fitting and over-smoothing in deep Graph Neural Networks for few-shot learning by proposing an Attentive GNN with a triple-attention mechanism, achieving promising results compared to state-of-the-art methods on mini-ImageNet and tiered-ImageNet benchmarks.
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks. Despite its powerful capacity to learn and generalize the model from few samples, GNN usually suffers from severe over-fitting and over-smoothing as the model becomes deep, which limit the scalability. In this work, we propose a novel Attentive GNN to tackle these challenges, by incorporating a triple-attention mechanism, i.e. node self-attention, neighborhood attention, and layer memory attention. We explain why the proposed attentive modules can improve GNN for few-shot learning with theoretical analysis and illustrations. Extensive experiments show that the proposed Attentive GNN model achieves the promising results, comparing to the state-of-the-art GNN- and CNN-based methods for few-shot learning tasks, over the mini-ImageNet and tiered-ImageNet benchmarks, under ConvNet-4 and ResNet-based backbone with both inductive and transductive settings. The codes will be made publicly available.