030e40e851 tuning for clustering by lstm and data_batching_new (make clustering module depart from prediction network)
Loading Heatmap…
m.maheri pushed to define_task at m.maheri/Melu_L2L_hyperTunning
2 years ago
m.maheri pushed to define_task at m.maheri/Melu_L2L_hyperTunning
- c701e2c338 only consider positive interaction for task embedding
2 years ago
m.maheri pushed to define_task at m.maheri/Melu_L2L_hyperTunning
- 5273533fc8 Revert "deep kmeans loss"
This reverts commit b4d130e2
- 07bb1cd89a check result of hyper tuning (best_result1)
- 3a3b256e65 Revert "prepare for hyper parameter tuning"
This reverts commit 576c0e97
- b4d130e28e deep kmeans loss
- dc38c4018f tanp loss (kl loss)
2 years ago
m.maheri pushed to RNN at m.maheri/MetaTL
- de53dda45f Implementing Robustify Negative sampling and undo prepossessing
2 years ago
m.maheri pushed to RNN at m.maheri/MetaTL
- 372e75db43 hyper parameter tuning including neg_size
2 years ago
m.maheri pushed to RNN at m.maheri/MetaTL
- c89c660a45 hyper parameter tuning including neg_size
- 8432f281de implement top1
- dca86acb3a implement bpr and bpr_max loss
- Compare 3 commits »
2 years ago
m.maheri pushed to RNN at m.maheri/MetaTL
- 6af0db43ad Distribute NS to all member of the sequence (except last item of seq in support-set)
2 years ago
m.maheri pushed to RNN at m.maheri/MetaTL
- 2a680a294f increase NS size (10X) + choose K most scored for NS
2 years ago
m.maheri pushed to RNN at m.maheri/MetaTL
- de111c73dc negative sampling by choosing from other user's items
2 years ago
m.maheri pushed to RNN at m.maheri/MetaTL
- b79f900501 make sampler to choose only sequenced items + write results
2 years ago
m.maheri pushed to RNN at m.maheri/MetaTL
- 5c17c5eb38 bug fixing for hyper parameter tuning
2 years ago
m.maheri pushed to RNN at m.maheri/MetaTL
- 6029ca93a1 using ray for hyper-parameter tanning
- 9cbfd2aff6 input all sequence of items to a LSTM (instead of averaging pairs)
- Compare 2 commits »
2 years ago