Topology-aware Reinforcement Feature Space Reconstruction for Graph Data

TL;DR

This paper introduces a topology-aware reinforcement learning framework that automatically reconstructs feature spaces for graph data by leveraging structural information, improving model performance without heavy manual tuning.

Contribution

It proposes a novel reinforcement learning approach that incorporates topological features and hierarchical agents for effective graph feature space reconstruction.

Findings

Enhanced feature space quality with topological information

Improved model generalization on graph datasets

Efficient reconstruction process demonstrated in experiments

Abstract

Feature space is an environment where data points are vectorized to represent the original dataset. Reconstructing a good feature space is essential to augment the AI power of data, improve model generalization, and increase the availability of downstream ML models. Existing literature, such as feature transformation and feature selection, is labor-intensive (e.g., heavy reliance on empirical experience) and mostly designed for tabular data. Moreover, these methods regard data samples as independent, which ignores the unique topological structure when applied to graph data, thus resulting in a suboptimal reconstruction feature space. Can we consider the topological information to automatically reconstruct feature space for graph data without heavy experiential knowledge? To fill this gap, we leverage topology-aware reinforcement learning to automate and optimize feature space reconstruction for graph data. Our approach combines the extraction of core subgraphs to capture essential structural information with a graph neural network (GNN) to encode topological features and reduce computing complexity. Then we introduce three reinforcement agents within a hierarchical structure to systematically generate meaningful features through an iterative process, effectively reconstructing the feature space. This framework provides a principled solution for attributed graph feature space reconstruction. The extensive experiments demonstrate the effectiveness and efficiency of including topological awareness.