DSL: Discriminative Subgraph Learning via Sparse Self-Representation

by   Lin Zhang, et al.

The goal in network state prediction (NSP) is to classify the global state (label) associated with features embedded in a graph. This graph structure encoding feature relationships is the key distinctive aspect of NSP compared to classical supervised learning. NSP arises in various applications: gene expression samples embedded in a protein-protein interaction (PPI) network, temporal snapshots of infrastructure or sensor networks, and fMRI coherence network samples from multiple subjects to name a few. Instances from these domains are typically "wide" (more features than samples), and thus, feature sub-selection is required for robust and generalizable prediction. How to best employ the network structure in order to learn succinct connected subgraphs encompassing the most discriminative features becomes a central challenge in NSP. Prior work employs connected subgraph sampling or graph smoothing within optimization frameworks, resulting in either large variance of quality or weak control over the connectivity of selected subgraphs. In this work we propose an optimization framework for discriminative subgraph learning (DSL) which simultaneously enforces (i) sparsity, (ii) connectivity and (iii) high discriminative power of the resulting subgraphs of features. Our optimization algorithm is a single-step solution for the NSP and the associated feature selection problem. It is rooted in the rich literature on maximal-margin optimization, spectral graph methods and sparse subspace self-representation. DSL simultaneously ensures solution interpretability and superior predictive power (up to 16 compared to baselines), with execution times up to an hour for large instances.


page 1

page 2

page 3

page 4


Supervised Feature Selection in Graphs with Path Coding Penalties and Network Flows

We consider supervised learning problems where the features are embedded...

Unsupervised Instance and Subnetwork Selection for Network Data

Unlike tabular data, features in network data are interconnected within ...

Structure and substructure connectivity of balanced hypercubes

The connectivity of a network directly signifies its reliability and fau...

Discriminative Feature Selection for Uncertain Graph Classification

Mining discriminative features for graph data has attracted much attenti...

Reconfiguring spanning and induced subgraphs

Subgraph reconfiguration is a family of problems focusing on the reachab...

Mining Brain Networks using Multiple Side Views for Neurological Disorder Identification

Mining discriminative subgraph patterns from graph data has attracted gr...

Fast Graph Construction Using Auction Algorithm

In practical machine learning systems, graph based data representation h...

Please sign up or login with your details

Forgot password? Click here to reset