meta-learning approach for solving cold start problem
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

options.py 602B

123456789101112131415161718192021222324252627
  1. config = {
  2. # item
  3. 'num_rate': 6,
  4. 'num_genre': 25,
  5. 'num_director': 2186,
  6. 'num_actor': 8030,
  7. 'embedding_dim': 32,
  8. 'first_fc_hidden_dim': 64,
  9. 'second_fc_hidden_dim': 64,
  10. # user
  11. 'num_gender': 2,
  12. 'num_age': 7,
  13. 'num_occupation': 21,
  14. 'num_zipcode': 3402,
  15. # cuda setting
  16. 'use_cuda': True,
  17. # model setting
  18. 'inner': 1,
  19. 'lr': 5e-5,
  20. 'local_lr': 5e-6,
  21. 'batch_size': 32,
  22. 'num_epoch': 20,
  23. # candidate selection
  24. 'num_candidate': 20,
  25. }
  26. states = ["warm_state", "user_cold_state", "item_cold_state", "user_and_item_cold_state"]