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

By Sofia Ira Ktena, Sarah Parisot, Enzo Ferrante, Martin Rajchl, M. J. Lee, Ben Glocker, Daniel Rueckert. 2017

216 citations recorded by the source corpus.

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. The choice of a distance or similarity metric is, however, not trivial and can be highly dependent on the application at hand. In this work, we propose a novel metric learning method to evaluate distance between graphs that leverages the power of convolutional neural networks, while exploiting concepts from spectral graph theory to allow these operations on irregular graphs. We demonstrate the potential of our method in the field of connectomics, where neuronal pathways or functional connections between brain regions are commonly modelled as graphs. In this problem, the definition of an appropriate graph similarity function is critical to unveil patterns of disruptions associated with certain brain disorders. 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.

Subfields: Artificial Intelligence, Molecular Biology, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Graph Learning

Citations in the corpus

Unsupervised Inductive Whole-Graph Embedding by Preserving Graph Proximity (2019, methodology): “Inspired by the recent progress on graph proximity modeling (Ktena et al., 2017; Bai et al., 2019), we propose a novel framework, UGRAPHEMB that employs multi-scale aggregations of node-level embeddings, guided by the graph-graph proximity defined by well-accepted and domain-agnostic graph proximity”
Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks (2017, methodology): “While in this work we apply multi-graph CNNs in the context of recommender systems to the graphs of users and items, however, our architecture is generic and can be used in other applications, such as neuroscience (autism detection with network of people and brain connectivity [31, 23]), computer gr”
Geometric Deep Learning: Going beyond Euclidean data (2016, methodology): “In a recent work from Imperial College [117], graph CNNs were used to detect disruptions of the brain functional networks associated with autism.”
Deep Learning on Graphs: A Survey (2018, unknown): “…recommendation [28], [66], [99], [134], chemistry and biology [46], [52], [55], [116], [117], physics [135], [136], disease and drug prediction [137], [138], [139], gene expression [140], natural language processing (NLP) [141], [142], computer vision [143], [144], [145], [146], [147], trafﬁc…”
Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer's disease (2018, methodology): “As an alternative, spectral methods have been used to learn a similarity metric between functional connectivity networks (Ktena et al., 2017), which was applied for Autism Spectrum Disorder (ASD) and sex classiﬁcation as well as manifold learning (Ktena et al., 2018).”
CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters (2017, background): “vision [2]–[6], brain imaging [7], and drug design [8] problems, to mention a few.”
Integrating Physics-Based Modeling with Machine Learning: A Survey (2020, background): “There is also recent work on encoding domain knowledge for geometric deep learning [34, 41] that is finding increasing use in computational chemistry [61, 70, 83], physics [18, 45], geostatistics [8, 272], and neuroscience [136].”
Robust Spatial Filtering With Graph Convolutional Neural Networks (2017, methodology): “For example, [11] and [10] use [12] to measure the similarity between functional brain graphs and document classification respectively.”
Optimal Transport for structured data with application on graphs (2018, background): “, 2016), brain connectivity (Ktena et al., 2017), or social networks (Yanardag & Vishwanathan, 2015).”
Graph Transformer Networks (2019, background): “The representation learnt by GNNs has been proven to be effective in achieving state-of-the-art performance in a variety of graph datasets such as social networks [7, 14, 35], citation networks [19, 33], functional structure of brains [20], recommender systems [1, 27, 39].”
Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems (2020, background): “There is also recent work on encoding domain knowledge in geometric deep learning [41, 50] that is finding increasing use in computational chemistry [71, 81, 95], physics [25, 54], hydrology [133], geostatistics [14, 294], and neuroscience [155].”
Graph Neural Networks and Their Current Applications in Bioinformatics (2021, background): “…(Zhang et al., 2018), image enhancement (Hu et al., 2020), registration (Hansen et al., 2019), retrieval (Zhai et al., 2019), brain connection (Ktena et al., 2017, 2018; Li X. et al., 2019a; Mirakhorli and Mirakhorli, 2019; Grigis et al., 2020; Li et al., 2020; Zhang and Pierre, 2020; Zhang…”