# Prediction of Links and Weights in Networks by Reliable Routes

## TL;DR

This paper introduces a method to predict missing links and their weights in networks, showing strong performance on real-world data including protein interactions.

## Contribution

The novel 'reliable-route method' extends unweighted similarity indices to weighted networks for link and weight prediction.

## Key findings

- The reliable-route method outperforms existing methods in predicting link weights in real-world networks.
- The method is highly accurate in predicting the existence of links, often being the best or near-best.
- Prediction accuracy is strongly correlated with the clustering coefficient of the network.

## Abstract

Link prediction aims to uncover missing links or predict the emergence of future relationships from the current network structure. Plenty of algorithms have been developed for link prediction in unweighted networks, but only a few have been extended to weighted networks. In this paper, we present what we call a “reliable-route method” to extend unweighted local similarity indices to weighted ones. Using these indices, we can predict both the existence of links and their weights. Experiments on various real-world networks suggest that our reliable-route weighted resource-allocation index performs noticeably better than others with respect to weight prediction. For existence prediction it is either the highest or very close to the highest. Further analysis shows a strong positive correlation between the clustering coefficient and prediction accuracy. Finally, we apply our method to the prediction of missing protein-protein interactions and their confidence scores from known PPI networks. Once again, our reliable-route method shows the highest accuracy.