search

hidasib / GRU4Rec

GRU4Rec is the original Theano implementation of the algorithm in "Session-based Recommendations with Recurrent Neural Networks" paper, published at ICLR 2016 and its follow-up "Recurrent Neural Networks with Top-k Gains for Session-based Recommendations". The code is optimized for execution on the GPU.
Other
754 stars 223 forks source link

NOT RNN MODEL #30

Closed yufengwhy closed 4 years ago

yufengwhy commented 5 years ago

The code only define a timestep of rnn, so gradient of timestep >=(t+2) cannot be propogated to timestep t ? which is more like a Markov Assumption (only timestep t and timestep t+1 have relations) rather than a rnn Assumption?

yufengwhy commented 5 years ago

In other words, the forward is like rnn, while the backward is like Markov model.

hidasib commented 4 years ago

If you are referring the lack of BPTT, check out issue #22 and the updated readme. The tl;dr version is that it doesn't improve performance on real life session data in experiments so was not included in the public version. Might be added later for folks working with longer sequences.