One Representative-Shot Learning Using a Population-Driven Template with Application to Brain Connectivity Classification and Evolution Prediction
This work addresses the problem of data scarcity in neuroimaging, particularly for rare diseases and low-resource clinical facilities, by enabling effective GNN training with minimal data, though it is incremental as it builds on existing CBT and GNN concepts.
The paper tackles the challenge of training graph neural networks (GNNs) on scarce neuroimaging data by introducing a one-shot learning paradigm using a single population-driven connectional brain template (CBT). It demonstrates that this method significantly outperforms benchmark one-shot learning methods and competes with conventional train-on-all strategies in classification and regression tasks.
Few-shot learning presents a challenging paradigm for training discriminative models on a few training samples representing the target classes to discriminate. However, classification methods based on deep learning are ill-suited for such learning as they need large amounts of training data --let alone one-shot learning. Recently, graph neural networks (GNNs) have been introduced to the field of network neuroscience, where the brain connectivity is encoded in a graph. However, with scarce neuroimaging datasets particularly for rare diseases and low-resource clinical facilities, such data-devouring architectures might fail in learning the target task. In this paper, we take a very different approach in training GNNs, where we aim to learn with one sample and achieve the best performance --a formidable challenge to tackle. Specifically, we present the first one-shot paradigm where a GNN is trained on a single population-driven template --namely a connectional brain template (CBT). A CBT is a compact representation of a population of brain graphs capturing the unique connectivity patterns shared across individuals. It is analogous to brain image atlases for neuroimaging datasets. Using a one-representative CBT as a training sample, we alleviate the training load of GNN models while boosting their performance across a variety of classification and regression tasks. We demonstrate that our method significantly outperformed benchmark one-shot learning methods with downstream classification and time-dependent brain graph data forecasting tasks while competing with the train-on-all conventional training strategy. Our source code can be found at https://github.com/basiralab/one-representative-shot-learning.