Counting 3,834 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
Apr. 23, 2019
Sep. 19, 2017


model image of TagSpace

Tensorflow implementation of Facebook #TagSpace

You can read more about #TagSpace from here

Special thanks to Facebook research team's Starspace project, it was really good reference.

Key Concept

Beside choosing 1000 random negative tag (for performance reason I guess), I choosed worst positive tag, best negative tag for calculating WARP loss. It's not good for performance but since we don't have much tags(labels) as Facebook, it seems okay.


Download ag news dataset as below

$ tree ./data
└── ag_news_csv
    ├── classes.txt
    ├── readme.txt
    ├── test.csv
    ├── train.csv
    └── train_mini.csv

and then

$ python


Accuracy 0.89 (ag test data, compare 0.91 from StarSpace with same condition [5 epoch, 10 dim])

To-do list

  • support multiple dataset
  • improve performance
  • adopt WARP sampling (now is just a WARP loss)
  • add Tensorboard metrics