RecBole icon indicating copy to clipboard operation
RecBole copied to clipboard

A unified, comprehensive and efficient recommendation library

Results 271 RecBole issues
Sort by recently updated
recently updated
newest added

**描述这个 bug** 请问能否添加模型-UltraGCN,该论文作者是贵校高瓴人工智能学院 Kelong Mao 和一众华为研究员,模型比Light快10倍。从研究所属和研究内容意义上来讲,本人认为值得加入您方的项目.

enhancement

**I think providing full legit tutorials for general/sequential/KG/context-aware models could be crucial to users and recbole's popularity.** It is nice to start with quick_start you provide. But as it is...

enhancement

Will multi-GPU be supported in the next version?

enhancement

Random walk method from *Updatable, Accurate, Diverse, and Scalable Recommendations for Interactive Applications* https://dl.acm.org/doi/10.1145/2955101

**描述这个 bug** 将SINE运行在ml-1m数据集上时,NDCG@10和HIT@10运行结果(NDCG@10=3.88,HIR@10=8.41)远低于原始论文中的结果(NDCG@10=7.06,HIR@10=16.34),认为结果异常。关键参数采用和原始论文一样的配置,即序列长度=20,embedding_size=128,λ=0.5,interest_size=4,concepts=50。请问导致这种问题的可能原因是什么? 以下是在ml-1m数据集上运行SINE时的相关配置及输出信息: 03 Mar 01:41 INFO General Hyper Parameters: gpu_id=0 use_gpu=True seed=2020 state=INFO reproducibility=False data_path=dataset/ml-1m Training Hyper Parameters: checkpoint_dir=saved epochs=500 train_batch_size=1024 learner=adam learning_rate=0.001 training_neg_sample_num=1 eval_step=1 stopping_step=5 Evaluation Hyper...

bug

首先非常喜欢贵团队的算法框架,由于本人目前在研究基于图网络的会话推荐模型,目前2021各种顶会涉及到的模型还是比较多的,尤其是基于用户兴趣融合建模的,比如SURGE,如贵团队将此类相关算法模型加以更新,那就太好了!

enhancement

Hi there, **I am a fan of the RecBole framework.** Considering the complexity of the RecBole framework, I provide an easy but feasible method to achieve multi-GPUs training. **The core...

**您希望添加的功能是否与某个问题相关?** recbole貌似没有支持MMOE、SNE和PLE这些多输出模型?不知道能否尝试支持下,还是说可以直接在现有框架里yy呢? **描述您希望的解决方案** model部分,可以输出多个预测结果;metric部分,可以对多个预测结果进行分别打分。导出部分, 支持对其中一个选定结果做保优。

enhancement

Both models from "Closed-Form Models for Collaborative Filtering with Side-Information" by Olivier Jeunen, et al. https://dl.acm.org/doi/abs/10.1145/3383313.3418480 These are variations of EASE which incorporate item token and token_seq features. Small accuracy...