Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks

@inproceedings{Ktena2017DistanceML,
  title={Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks},
  author={Sofia Ira Ktena and Sarah Parisot and Enzo Ferrante and Martin Rajchl and M. J. Lee and Ben Glocker and Daniel Rueckert},
  booktitle={MICCAI},
  year={2017}
}
Evaluating similarity between graphs is of major importance in several computer vision and pattern recognition problems, where graph representations are often used to model objects or interactions between elements. [] Key Result Experimental results on the ABIDE dataset show that our method can learn a graph similarity metric tailored for a clinical application, improving the performance of a simple k-nn classifier by 11.9% compared to a traditional distance metric.

Understanding Graph Isomorphism Network for Brain MR Functional Connectivity Analysis

TLDR
A framework for analyzing the fMRI data using the Graph Isomorphism Network (GIN), which was recently proposed as a state-of-the-art GNN for graph classification, is developed and the obtained saliency map show high correspondence with previous neuroimaging evidences related to sex differences.

Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis

TLDR
This paper develops a framework for analyzing the fMRI data using the Graph Isomorphism Network (GIN), which was recently proposed as a powerful GNN for graph classification, and validate the proposed framework using large-scale resting-state fMRI (rs-fMRI) data for classifying the sex of the subject based on the graph structure of the brain.

Learning Similarity-Preserving Representations of Brain Structure-Function Coupling

TLDR
A supervised graph representation learning framework to model the relationship between brain structural connectivity and functional connectivity via a graph encoder- decoder system and proposes a Siamese network architecture equipped with graph convolutional encoders to learn graph-level embeddings that preserve application-dependent similarity measures between brain networks.

Deep Hypergraph U-Net for Brain Graph Embedding and Classification

TLDR
The proposed Hypergraph U-Net (HUNet), a novel data embedding framework leveraging the hypergraph structure to learn low-dimensional embeddings of data samples while capturing their high-order relationships, demonstrates both scalability and generalizability.

Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention

TLDR
STAGIN is proposed, a method for learning dynamic graph representation of the brain connectome with spatio-temporal attention that combines novel READOUT functions and the Transformer encoder to provide spatial and temporal explainability with attention.

Graph Neural Networks and Their Current Applications in Bioinformatics

TLDR
It is believed that GNNs are potentially an excellent method that solves various biological problems in bioinformatics research and have a long road ahead.

Template based Graph Neural Network with Optimal Transport Distances

TLDR
This work proposes a novel point of view, which places distances to some learnable graph templates at the core of the graph representation, and empirically validate its claim on several synthetic and real life graph classification datasets, where it is competitive or surpasses kernel and GNN state-of-the-art approaches.

Learning-Based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching

TLDR
The model, Graph-Sim, achieves the state-of-the-art performance on four real-world graph datasets under six out of eight settings, compared to existing popular methods for approximate Graph Edit Distance (GED) and Maximum Common Subgraph (MCS) computation.
...

References

SHOWING 1-10 OF 16 REFERENCES

Learning Convolutional Neural Networks for Graphs

TLDR
This work proposes a framework for learning convolutional neural networks for arbitrary graphs that operate on locally connected regions of the input and demonstrates that the learned feature representations are competitive with state of the art graph kernels and that their computation is highly efficient.

Semi-Supervised Classification with Graph Convolutional Networks

TLDR
A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.

Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs

TLDR
This paper proposes a unified framework allowing to generalize CNN architectures to non-Euclidean domains (graphs and manifolds) and learn local, stationary, and compositional task-specific features and test the proposed method on standard tasks from the realms of image-, graph-and 3D shape analysis and show that it consistently outperforms previous approaches.

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

TLDR
This work presents a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs.

Graph-Based Inter-Subject Pattern Analysis of fMRI Data

TLDR
A novel classification framework based on group-invariant graphical representations is introduced, allowing to overcome the inter-subject variability present in functional magnetic resonance imaging (fMRI) data and to perform multivariate pattern analysis across subjects.

The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains

TLDR
This tutorial overview outlines the main challenges of the emerging field of signal processing on graphs, discusses different ways to define graph spectral domains, which are the analogs to the classical frequency domain, and highlights the importance of incorporating the irregular structures of graph data domains when processing signals on graphs.

Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimizing Global Loss Functions

TLDR
A combination of the triplet and global losses produces the best embedding in the field, using this triplet network, and it is demonstrated that the use of the central-surround siamese network trained with the global loss producing the best result of the field on the UBC dataset.

Efficient graphlet kernels for large graph comparison

TLDR
In this article, two theoretically grounded speedup schemes are introduced, one based on sampling and the second specifically designed for bounded degree graphs, to efficiently compare large graphs that cannot be tackled by existing graph kernels.

Learning to compare image patches via convolutional neural networks

TLDR
This paper shows how to learn directly from image data a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems, and opts for a CNN-based model that is trained to account for a wide variety of changes in image appearance.