LGCVMar 10, 2014

Sublinear Models for Graphs

arXiv:1403.2295v1
Originality Synthesis-oriented
AI Analysis

This work addresses graph classification problems, but it appears incremental as it adapts linear model concepts to graphs without major breakthroughs.

The paper extends linear models to sublinear models for graphs, providing a geometric interpretation, a learning rule, convergence theorem, and VC-dimension analysis, with empirical results showing similar properties to linear models on graph data.

This contribution extends linear models for feature vectors to sublinear models for graphs and analyzes their properties. The results are (i) a geometric interpretation of sublinear classifiers, (ii) a generic learning rule based on the principle of empirical risk minimization, (iii) a convergence theorem for the margin perceptron in the sublinearly separable case, and (iv) the VC-dimension of sublinear functions. Empirical results on graph data show that sublinear models on graphs have similar properties as linear models for feature vectors.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes