T H

https://github.com/XiaoMi/chronos/blob/92e4a30c98947e87aba47ea88c944a56505a4ec0/chronos-client/src/main/java/com/xiaomi/infra/chronos/client/ChronosClientWatcher.java#L220

【序列推荐】测试数据集的session id不在训练数据集中，请问这种情况RecBole能处理吗？

1

具体情况是这样，数据集分两种： train数据集，session id是从0-199999， test数据集，session id是从200000-250000 现在我用train数据集训练得到序列模型SRGNN。 然后我想用得到的模型对test数据集做预测，（注意模型并没有见过test数据集），应该怎么做？

How to build interaction for the method 'full_sort_predict'?

1

https://github.com/RUCAIBox/RecBole/blob/4121d5c2a7c4813566d2240e5d474d6ce2f0929f/recbole/model/sequential_recommender/srgnn.py#L247

# ❓ How to print metrics while training? I want to drive the Transformers4Rec to print metrics every N step, but there is no document about it yet. Thank you.

# ❓ Cross-entropy and pairwise losses are supported in Next Item Prediction I found the text as following on page https://nvidia-merlin.github.io/Transformers4Rec/stable/model_definition.html?highlight=pairwise%20loss Next Item Prediction: Predicts next items for a given...

同样是Session Based Recommendation算法，为什么GRU4Rec是用于召回，而BERT4Rec用于排序？

1

谢谢！

为什么这个项目会依赖tensorflow？

2

REQUIRED_PACKAGES = [ 'torch>=1.2.0', 'tqdm', 'scikit-learn', 'tensorflow' ] 我可以删掉setup.py中的tensorflow吗？

How to generate a list of items as the recommendation result?

1

thank you!

请问General Recommendation的边是否能设置权重？

3

谢谢！

hi, this repo is a nice job. But, I can not find a method to make the NBFNet to predict. For example, given a (head, relation) and get a list...