GNN-based Unified Deep Learning
By: Furkan Pala, Islem Rekik
Potential Business Impact:
Helps AI learn from different medical images.
Deep learning models often struggle to maintain generalizability in medical imaging, particularly under domain-fracture scenarios where distribution shifts arise from varying imaging techniques, acquisition protocols, patient populations, demographics, and equipment. In practice, each hospital may need to train distinct models - differing in learning task, width, and depth - to match local data. For example, one hospital may use Euclidean architectures such as MLPs and CNNs for tabular or grid-like image data, while another may require non-Euclidean architectures such as graph neural networks (GNNs) for irregular data like brain connectomes. How to train such heterogeneous models coherently across datasets, while enhancing each model's generalizability, remains an open problem. We propose unified learning, a new paradigm that encodes each model into a graph representation, enabling unification in a shared graph learning space. A GNN then guides optimization of these unified models. By decoupling parameters of individual models and controlling them through a unified GNN (uGNN), our method supports parameter sharing and knowledge transfer across varying architectures (MLPs, CNNs, GNNs) and distributions, improving generalizability. Evaluations on MorphoMNIST and two MedMNIST benchmarks - PneumoniaMNIST and BreastMNIST - show that unified learning boosts performance when models are trained on unique distributions and tested on mixed ones, demonstrating strong robustness to unseen data with large distribution shifts. Code and benchmarks: https://github.com/basiralab/uGNN
Similar Papers
uGMM-NN: Univariate Gaussian Mixture Model Neural Network
Machine Learning (CS)
Makes computers understand and guess better.
Universal Graph Learning for Power System Reconfigurations: Transfer Across Topology Variations
Systems and Control
Lets power grids learn new setups instantly.
Enhanced Pre-training of Graph Neural Networks for Million-Scale Heterogeneous Graphs
Machine Learning (CS)
Teaches computers to learn from messy, mixed-up data.