arXiv:2511.13645v2 Announce Type: replace 
Abstract: Operational knowledge-graph (KG) pipelines in networking and cybersecurity increasingly need to refresh embeddings under strict time, memory, and audit budgets, especially as curated feeds and LLM-assisted extraction accelerate KG updates. A recurring per-step cost in mini-batch KG learning is neighborhood-context estimation: uniform neighbor sampling without replacement followed by mean aggregation. Common frameworks implement this estimator through sampled-subgraph materialization and intermediate feature gathers, adding kernel launches, allocator pressure, and transient memory spikes. We present One-Pass Neighborhood Estimation, a fused PyTorch CUDA operator that samples neighbors and directly emits the sampled-neighborhood mean, avoiding explicit block construction while preserving GraphSAGE-mean semantics for the same sampled neighbor IDs. It supports seed-controlled sampling and optional saved-index replay for reproducible validation and regression testing. Across large-graph mini-batch workloads, it improves FP32 end-to-end step latency by 2.24x-3.48x over tuned DGL baselines and reduces transient GPU memory by up to 160x in our measurements. On OGB KG completion benchmarks such as WikiKG2 and BioKG, it reduces step time and peak VRAM while matching ranking quality within seed variability, improving time-to-quality for budgeted KG refresh.

تم تقديم FuseSampleAgg، وهو مشغل PyTorch CUDA، لتمكين تقدير الجوار بكفاءة في خطوة واحدة لتحديث والتحقق من صحة الرسوم البيانية للمعرفة، مما يعالج التحديات المتعلقة بتحديثات التضمينات في الشبكات والأمن السيبراني تحت قيود صارمة للموارد.

La reciente introducción de FuseSampleAgg, un operador de PyTorch CUDA, permite una estimación eficiente del vecindario en un solo paso para la actualización y validación de grafos de conocimiento, abordando los desafíos de las actualizaciones de embeddings en redes y ciberseguridad bajo estrictas limitaciones de recursos.

La récente introduction de FuseSampleAgg, un opérateur PyTorch CUDA, permet une estimation efficace du voisinage en un seul passage pour le rafraîchissement et la validation des graphes de connaissances, répondant aux défis des mises à jour d'embeddings dans les réseaux et la cybersécurité sous des contraintes de ressources strictes.

The recent introduction of FuseSampleAgg, a PyTorch CUDA operator, enables efficient one-pass neighborhood estimation for knowledge-graph refresh and validation, addressing the challenges of embedding updates in networking and cybersecurity under strict resource constraints.