NeSy-Edge: Neuro-Symbolic Trustworthy Self-Healing in the Computing Continuum

TL;DR

NeSy-Edge is a neuro-symbolic framework designed for trustworthy self-healing in the computing continuum, enabling resource-efficient, robust root-cause analysis and recovery in noisy, heterogeneous edge environments.

Contribution

It introduces a novel edge-first neuro-symbolic approach that converts logs into causal graphs for effective self-healing, addressing limitations of static and heavy fault-management methods.

Findings

Achieves up to 75% root-cause analysis accuracy under high noise.

Maintains 65% end-to-end diagnosis accuracy with limited memory.

Operates within approximately 1500 MB of local memory.

Abstract

The computational demands of modern AI services are increasingly shifting execution beyond centralized clouds toward a computing continuum spanning edge and end devices. However, the scale, heterogeneity, and cross-layer dependencies of these environments make resilience difficult to maintain. Existing fault-management methods are often too static, fragmented, or heavy to support timely self-healing, especially under noisy logs and edge resource constraints. To address these limitations, this paper presents NeSy-Edge, a neuro-symbolic framework for trustworthy self-healing in the computing continuum. The framework follows an edge-first design, where a resource-constrained edge node performs local perception and reasoning, while a cloud model is invoked only at the final diagnosis stage. Specifically, NeSy-Edge converts raw runtime logs into structured event representations, builds a prior-constrained sparse symbolic causal graph, and integrates causal evidence with historical troubleshooting knowledge for root-cause analysis and recovery recommendation. We evaluate our work on representative Loghub datasets under multiple levels of semantic noise, considering parsing quality, causal reasoning, end-to-end diagnosis, and edge-side resource usage. The results show that NeSy-Edge remains robust even at the highest noise level, achieving up to 75% root-cause analysis accuracy and 65% end-to-end accuracy while operating within about 1500 MB of local memory.