I have created a set of nodes (archaeological sites) and ties (connected via certain geographical distances), exported from QGIS. I now have an edge list with weights (distances). Gephi, however, sees larger numbers as stronger weights, when in reality they represent weaker weights as they are distances. Will the network math work properly if I use the inverse of the distances as weight numbers?

1 Answer 1


No one offered an answer, so I will add some information that might be useful to others in the future.

I put my data into Gephi in three forms: weighted, with inverse weights, and with no weights.

All the standard node measures were the same in all three graphs.

The difference came in assessing Modularity. The weighted and no weights produced similar results (33 and 34), but inverse produced 25. So there is clearly a difference in assessing the overall coherence of the graph. I need to check the resulting modules in QGIS to see which makes more sense.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.