Topology-Driven Edge Predictions with Graph Machine Learning for Optical Network Growth.

Akanksha Ahuja, Sam Nallaperuma Herzberg,Albert Rafel,Paul Wright,Andrew Lord,Seb J. Savory

Optical Fiber Communications Conference and Exhibition（2024）

Cited 0|Views9

No score

Abstract

Graph representation learning on real-world optical core networks outperforms edge prediction heuristics by 10 times, achieving up to 93.4% accuracy on BT(UK), COST(EU), and CORONET(USA) by learning from 10% training data.

Translated text

Key words

Machine Learning,Network Growth,Optical Networks,Heuristic,Training Data,Binary Classification,Network Topology,Random Walk,Intersection Over Union,Topological Structure,Network Design,PageRank,Network Expansion,Optic Cables,Link Prediction,Node Embeddings,Machine Learning Pipeline,Network Planning,Multiple Orders Of Magnitude

AI Read Science

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Chat Paper

Summary is being generated by the instructions you defined