Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification

TL;DR

This paper introduces SLIM, a neural network model that addresses resolution dilemmas in graph classification, improving interpretability and accuracy by explicitly modeling component interactions.

Contribution

The paper proposes SLIM, a novel neural network that tackles resolution dilemmas in graph classification, enhancing interpretability and predictive performance through explicit interaction modeling.

Findings

SLIM outperforms traditional models in accuracy.

SLIM provides better interpretability of graph components.

Explicit interaction modeling improves classification results.

Abstract

Graph neural networks are promising architecture for learning and inference with graph-structured data. Yet difficulties in modelling the ``parts'' and their ``interactions'' still persist in terms of graph classification, where graph-level representations are usually obtained by squeezing the whole graph into a single vector through graph pooling. From complex systems point of view, mixing all the parts of a system together can affect both model interpretability and predictive performance, because properties of a complex system arise largely from the interaction among its components. We analyze the intrinsic difficulty in graph classification under the unified concept of ``resolution dilemmas'' with learning theoretic recovery guarantees, and propose ``SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling. It turns out, that by solving the resolution dilemmas, and leveraging explicit interacting relation between component parts of a graph to explain its complexity, SLIM is more interpretable, accurate, and offers new insight in graph representation learning.