# A Few-shot Learning Graph Multi-Trajectory Evolution Network for Forecasting Multimodal Baby Connectivity Development from a Baseline Timepoint

arXiv: https://arxiv.org/abs/2110.03535 · HTML: https://mlsanity.com/paper/2110.03535/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 6 Oct 2021.

## Builds on (most cited first, 13 of 13)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A survey on domain adaptation theory: learning bounds and theoretical guarantees](https://mlsanity.com/paper/2004.11829/) (2020)
- [Graph Neural Networks in Network Neuroscience](https://mlsanity.com/paper/2106.03535/) (2021)
- [Knowledge distillation from multi-modal to mono-modal segmentation networks](https://mlsanity.com/paper/2106.09564/) (2021)
- [Self-supervised Knowledge Distillation for Few-shot Learning](https://mlsanity.com/paper/2006.09785/) (2020)
- [Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation](https://mlsanity.com/paper/2007.10787/) (2020)
- [Domain Adaptation on Graphs by Learning Aligned Graph Bases](https://mlsanity.com/paper/1803.05288/) (2018)
- [Difficulty-aware Meta-learning for Rare Disease Diagnosis](https://mlsanity.com/paper/1907.00354/) (2019)
- [Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy](https://mlsanity.com/paper/2006.14811/) (2020)
- [Deep EvoGraphNet Architecture For Time-Dependent Brain Graph Data Synthesis From a Single Timepoint](https://mlsanity.com/paper/2009.13217/) (2020)
- [Residual Embedding Similarity-Based Network Selection for Predicting Brain Network Evolution Trajectory from a Single Observation](https://mlsanity.com/paper/2009.11110/) (2020)
- [Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification](https://mlsanity.com/paper/2007.05009/) (2020)

## Built on by (most cited first, 1 of 1)

- [Predicting Infant Brain Connectivity with Federated Multi-Trajectory GNNs using Scarce Data](https://mlsanity.com/paper/2401.01383/) (2024)

## Abstract (arXiv)

Charting the baby connectome evolution trajectory during the first year after birth plays a vital role in understanding dynamic connectivity development of baby brains. Such analysis requires acquisition of longitudinal connectomic datasets. However, both neonatal and postnatal scans are rarely acquired due to various difficulties. A small body of works has focused on predicting baby brain evolution trajectory from a neonatal brain connectome derived from a single modality. Although promising, large training datasets are essential to boost model learning and to generalize to a multi-trajectory prediction from different modalities (i.e., functional and morphological connectomes). Here, we unprecedentedly explore the question: Can we design a few-shot learning-based framework for predicting brain graph trajectories across different modalities? To this aim, we propose a Graph Multi-Trajectory Evolution Network (GmTE-Net), which adopts a teacher-student paradigm where the teacher network learns on pure neonatal brain graphs and the student network learns on simulated brain graphs given a set of different timepoints. To the best of our knowledge, this is the first teacher-student architecture tailored for brain graph multi-trajectory growth prediction that is based on few-shot learning and generalized to graph neural networks (GNNs). To boost the performance of the student network, we introduce a local topology-aware distillation loss that forces the predicted graph topology of the student network to be consistent with the teacher network. Experimental results demonstrate substantial performance gains over benchmark methods. Hence, our GmTE-Net can be leveraged to predict atypical brain connectivity trajectory evolution across various modalities. Our code is available at https: //github.com/basiralab/GmTE-Net.