The content implications of [data/cora/cora.features].

thunlp / OpenNE

An Open-Source Package for Network Embedding (NE)

MIT License

1.68k stars 485 forks source link

The content implications of [data/cora/cora.features]. #94

Closed ternencez closed 4 years ago

ternencez commented 4 years ago

What does the content of [data/cora/cora.features] in the dataset represent? The first digit represents the node number, and the remaining 1,433 digits represent the feature values. So how did the 1,433 character Numbers come about?

cgq15 commented 4 years ago

Nodes in Cora are papers and the associated features are bag-of-words vectors of them.