Differentially Describing Groups of Graphs

@inproceedings{Coupette2022DifferentiallyDG,
  title={Differentially Describing Groups of Graphs},
  author={Corinna Coupette and Sebastian Dalleiger and Jilles Vreeken},
  booktitle={AAAI},
  year={2022}
}
How does neural connectivity in autistic children differ from neural connectivity in healthy children or autistic youths? What patterns in global trade networks are shared across classes of goods, and how do these patterns change over time? Answering questions like these requires us to differentially describe groups of graphs: Given a set of graphs and a partition of these graphs into groups, discover what graphs in one group have in common, how they systematically differ from graphs in other… 

Figures from this paper

References

SHOWING 1-10 OF 52 REFERENCES

Explainable Classification of Brain Networks via Contrast Subgraphs

TLDR
A novel approach for classifying brain networks based on extracting contrast sub graphs, i.e., a set of vertices whose induced subgraphs are dense in one class of graphs and sparse in the other, is introduced.

Common and individual structure of brain networks

TLDR
The proposed Multiple GRAph Factorization (M-GRAF) model relies on a logistic regression mapping combined with a hierarchical eigenvalue decomposition and an efficient algorithm for estimation and basic properties of the approach are developed.

Bayesian Inference and Testing of Group Differences in Brain Networks

TLDR
A general Bayesian procedure for inference and testing of group differences in the network structure, which relies on a nonparametric representation for the conditional probability mass function associated with a network-valued random variable, is developed.

Multiscale null hypothesis testing for network‐valued data: Analysis of brain networks of patients with autism

TLDR
A general non-parametric finite-sample exact statistical framework that allows to test for differences in connectivity within and between pre-specified areas inside the brain network, with strong control of the family-wise error rate is proposed.

Hypothesis Testing For Network Data in Functional Neuroimaging

TLDR
This work draws on concepts and techniques from geometry, and high-dimensional statistical inference, for testing in the context of networks derived from functional neuroimaging data on human subjects from the 1000 Functional Connectomes Project, and shows that this global test is more statistical powerful, than a mass-univariate approach.

A cross-disorder connectome landscape of brain dysconnectivity

TLDR
A cross-disorder ‘connectome landscape of dysconnectivity’ is outlined along principal dimensions of network organization that may place shared connectome alterations between brain disorders in a common framework.

Generalizability and reproducibility of functional connectivity in autism

TLDR
Overall, functional connectivity features predictive of autism demonstrated limited generalizability across sites, with consistent results only for large samples.

Model-based clustering for populations of networks

TLDR
This work proposes a model-based clustering method based on mixtures of generalized linear (mixed) models that can be employed to describe the joint distribution of a populations of networks in a parsimonious manner and to identify subpopulations of networks that share certain topological properties of interest.

Developmental changes in large-scale network connectivity in autism

...