SCGNN: Semantic Consistency enhanced Graph Neural Network Guided by Granular-ball Computing

2026-05-04

AI Summary

This work addresses the scalability and robustness limitations of existing graph neural networks (GNNs), which rely on computationally expensive node-level exhaustive search to model semantic consistency among nodes. To overcome this, the authors propose SCGNN, a plug-and-play framework that introduces granular ball computing (GBC) into GNNs for the first time. By adaptively aggregating nodes into granular balls, SCGNN replaces node-level matching with group-level semantic structures, substantially reducing computational overhead while enhancing noise resilience. The method integrates anchor-based graph construction and a label consistency check (LCC) mechanism, injecting semantic consistency signals through dual strategies of structural and supervised enhancement. Compatible with various GNN backbones, SCGNN demonstrates superior representation learning quality and robustness without compromising efficiency, as validated by extensive experiments.

Abstract

Capturing semantic consistency among nodes is crucial for effective graph representation learning. Existing approaches typically rely on $k$-nearest neighbors ($k$NN) or other node-level full search algorithms (FSA) to mine semantic relationships via exhaustive pairwise similarity computation, which suffer from high computational complexity and rigid neighbor selection, limiting scalability and introducing noisy connections. In this paper, we propose the Semantic Consistency enhanced Graph Neural Network (SCGNN), a novel plug-and-play framework that leverages granular-ball computing (GBC) to efficiently capture semantic consistency in a scalable manner. Unlike node-level FSA methods, SCGNN models group-level semantic structure by adaptively partitioning nodes into granular balls, significantly reducing computational cost while improving robustness to noise. To effectively utilize the discovered group-level semantic consistency, we design a dual enhancement strategy. Specifically, (1) a structure enhancement module constructs an anchor-based graph structure, where each anchor is a virtual node representing the group-level semantic carried by a granular ball, then injecting group-level semantic information into the graph structure; and (2) a supervision enhancement module performs label consistency checking (LCC) by combining GBC predictions with model-generated pseudo-labels, thereby producing more reliable supervision signals. SCGNN is compatible with various GNN backbones. During the forward propagation of SCGNN, the vanilla graph and the augment graph are jointly encoded, and their predictions are fused; during the backpropagation, the supervision enhancement module provides enhanced supervision signals to guide parameter updates.

Problem

• semantic consistency
• graph neural network
• computational complexity
• noisy connections
• scalability

Innovation

• Granular-ball Computing
• Semantic Consistency
• Graph Neural Network
• Scalable Representation Learning
• Label Consistency Checking