Wicknight
Wicknight
> @Wicknight Thanks for your advice again. Now I just tested the FISSA and SASRec models with all default settings on the ml-100k dataset, which means they use almost all...
> @Wicknight Thank you for your comments. Is there anything need to be improved? Thank you for your support. I am testing on other datasets and waiting for the results....
@Tokkiu During the test, I had a little doubt about the candidate items in line 116 and line 117. All items are used as candidate items in the code here....
> @Wicknight Thanks for your concern. According to the paper, they adopt binary cross-entropy. Whereas we usually use CE and BPR in recbole for most sequential models. I also think...
> > > @Wicknight Thanks for your concern. According to the paper, they adopt binary cross-entropy. Whereas we usually use CE and BPR in recbole for most sequential models. I...
> > > > > @Wicknight Thanks for your concern. According to the paper, they adopt binary cross-entropy. Whereas we usually use CE and BPR in recbole for most sequential...
> > > > Yes, did you test on them？How about performance gap？ First of all, thank you for your PR and efforts to RecBole! I didn't test on all...
@caijie1998 Please check whether your local files are complete, for example, check whether the recbole/utils/__ init__. py and rebole/utils/logger.py are complete. Under normal circumstances, this error will not occur if...
Since there is no new reply for a long time, the issue has been closed. If you have any questions, please feel free to comment.
@QinHsiu 您好！感谢您对伯乐的关注与支持！ 1.序列推荐模型往往需要大量的训练数据才能达到比较良好的结果，如果不进行这样的数据增强，序列化数据的量可能并不足够； 2.序列数据往往都是非定长的，有些用户一次就能找到自己想要的，而有些需要大量点击后才能找到自己想要的，所以序列数据中的每个点击其实都是有意义的，这里我们将每一个time-stamp的点击都视为训练样本，并且通过max_item_list_len和pad将序列处理为定长。这里我们参考了[“Improved Recurrent Neural Networks for Session-based Recommendations”](https://arxiv.org/abs/1606.08117)的处理方式； 3.如果您想使用其它的数据增强方式，您可以修改我们的data_augmentation函数来实现；如果您不想使用数据增强方法，您可以提前处理好数据，然后使用 benchmark_filename 这个参数直接加载处理好的（自定义划分后的）数据，详情请参考 [session_based_rec_example.py](https://github.com/RUCAIBox/RecBole/blob/master/run_example/session_based_rec_example.py)。