Binary-to-Decimal Encoding-Based Performance Predictor for Evolutionary Graph Fusion Architecture Search and Applications to Medical Data

Aohan Mei, Nan Li, Lianbo Ma, Kaizhou Gao, Min Huang, Bing Xue, Yaochu Jin

Abstract: Benefiting from the principles of information aggregation and multi-layer stacking, graph neural networks (GNNs) have achieved remarkable success in graph-structured data tasks. However, deeper GNNs often suffer from over-smoothing, which weakens node-level discrimination. To address this, skip connections and feature fusion techniques have been introduced, but the manual design of these strategies typically require significant computational resources and expert knowledge. Inspired by neural architecture search (NAS), this paper proposes EGFAS-BD, an evolutionary framework for graph fusion architecture search with a binary-to-decimal encoding-based performance predictor. This is an evolutionary algorithm (EA)-based framework specifically designed for graph fusion scenarios. We first construct an expanded search space integrating diverse aggregation and fusion operations to enhance architectural expressiveness. A compact binary-to-decimal encoding scheme is then used to improve information density, reducing storage overhead and simplifying predictor training. Additionally, we introduce an active filling strategy based on core-set selection, which leverages population-level distributions to enhance sampling efficiency and prediction accuracy. Experiments on eight benchmark datasets and three real-world medical graph datasets demonstrate that EGFAS-BD outperforms state-of-the-art NAS methods in both search efficiency and generalization performance. Ablation studies further verify that the proposed encoding and prediction strategies significantly accelerate convergence and reduce computational cost.

External IDs:doi:10.1109/tevc.2025.3639127