Graph Neural Networks With Triple Attention for Few-Shot Learning

Abstract

Recent advances in Graph Neural Networks (GNNs) have achieved superior results in many challenging tasks, such as few-shot learning. Despite its capacity to learn and generalize a model from only a few annotated samples, GNN is limited in scalability, as deep GNN models usually suffer from severe over-fitting and over-smoothing. In this work, we propose a novel GNN framework with a triple-attention mechanism, i.e., node self-attention, neighbor attention, and layer memory attention, to tackle these challenges. We provide both theoretical analysis and illustrations to explain why the proposed attentive modules can improve GNN scalability for few-shot learning tasks. Our experiments show that the proposed Attentive GNN model outperforms the state-of-the-art few-shot learning methods using both GNN and non-GNN approaches. The improvement is consistent over the mini-ImageNet, tiered-ImageNet, CUB-200-2011, and Flowers-102 benchmarks, using both ConvNet-4 and ResNet-12 backbones, and under both the inductive and transductive settings. Furthermore, we demonstrate the superiority of our method for few-shot fine-grained and semi-supervised classification tasks with extensive experiments. The code for this work is publicly available at https://github.com/chenghao-ch94/AGNN.

Situational awareness on a graph: towards graph neural networks for spectrum analysis and battlefield management

“…15 Examples of attributed networks include citation networks, social networks, biological networks, and critical infrastructure networks, making them directly applicable to battlefield and spectrum management graphs. Much like others who have adopted the attention mechanism in GNN few-shot learning for computer vision, 16 Wang augments the GNN with attention, but moves it to the attribute level, thus enabling few-shot learning on traditional graph structured data.…”

Image classification with limited data information

“…In this work, we propose an attentive graph neural network (AGNN) [136,137] with a novel triple-attention mechanism, i.e., node self-attention, neighbor atten- The contributions of this work are summarized as follows,…”