Spiking Graph Predictive Coding for Reliable OOD Generalization

2026-02-22

AI Summary

This work addresses the challenge of unstable and overconfident predictions in graph neural networks (GNNs) under out-of-distribution (OOD) shifts in real-world web environments, where reliable and interpretable uncertainty estimation is often lacking. To this end, the authors propose SIGHT, a novel module that, for the first time, integrates predictive coding mechanisms with spiking graph representations. By performing iterative error-driven correction on spiking graph states, SIGHT enables endogenous, spatially localizable uncertainty awareness. Unlike conventional post-hoc calibration approaches, SIGHT operates intrinsically and can be seamlessly plugged into existing GNN architectures. Extensive experiments demonstrate that SIGHT significantly improves prediction accuracy, calibration quality, and interpretability across multiple graph benchmarks and OOD scenarios.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Graphical Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Graphs provide a powerful basis for modeling Web-based relational data, with expressive GNNs to support the effective learning in dynamic web environments. However, real-world deployment is hindered by pervasive out-of-distribution (OOD) shifts, where evolving user activity and changing content semantics alter feature distributions and labeling criteria. These shifts often lead to unstable or overconfident predictions, undermining the trustworthiness required for Web4Good applications. Achieving reliable OOD generalization demands principled and interpretable uncertainty estimation; however, existing methods are largely post-hoc, insensitive to distribution shifts, and unable to explain where uncertainty arises especially in high-stakes settings. To address these limitations, we introduce SpIking GrapH predicTive coding (SIGHT), an uncertainty-aware plug-in graph learning module for reliable OOD Generalization. SIGHT performs iterative, error-driven correction over spiking graph states, enabling models to expose internal mismatch signals that reveal where predictions become unreliable. Across multiple graph benchmarks and diverse OOD scenarios, SIGHT consistently enhances predictive accuracy, uncertainty estimation, and interpretability when integrated with GNNs.

Problem

• out-of-distribution generalization
• graph neural networks
• uncertainty estimation
• distribution shift
• interpretability

Innovation

• Spiking Neural Networks
• Predictive Coding
• Out-of-Distribution Generalization
• Graph Neural Networks
• Uncertainty Quantification