The implementation of “A Capsule Network for Recommendation and Explaining What You Like and Dislike”, Chenliang Li, Cong Quan, Li Peng, Yunwei Qi, Yuming Deng, Libing Wu, https://dl.acm.org/citation.cfm?doid=3331184.3331216
Hi, thanks for sharing your implementation.
I tried to reuse your code on Amazon datasets, but I didn't get the performance as expected.
For the word embedding, I tried to use Glove pretrained embedding at first and then turned to randomly initialization.
I set the maximum document length to be 500, which is the default value provided in code.
I doubt whether I made some mistakes in parameter settings.