RUCAIBox / RecBole

A unified, comprehensive and efficient recommendation library
https://recbole.io/
MIT License
3.47k stars 615 forks source link

[🐛BUG] DCN在mvlen100k下uni100与full的AUC差距过大 #2117

Open cywuuuu opened 3 days ago

cywuuuu commented 3 days ago

描述这个 bug 对 bug 作一个清晰简明的描述。 DCN在mvlen100k下uni100与full的AUC差距过大, uni100时auc仅0.58左右,而full时auc为0.78左右,请问原因?谢谢 如何复现 复现这个 bug 的步骤:

  1. 您引入的额外 yaml 文件
    
    load_col:
    inter: ['user_id', 'item_id', 'rating', 'timestamp']
    user: ['user_id', 'age', 'gender', 'occupation']
    item: ['item_id', 'release_year', 'class']
    threshold: {'rating': 4}
    normalize_all: True
    # model config
    embedding_size: 10
    # Training and evaluation config
    epochs: 500
    train_batch_size: 4096
    eval_batch_size: 4096

topk: [1,2,3, 10, 100] train_neg_sample_args: ~ metrics: ['AUC'] valid_metric: AUC

eval_args:

mode: uni100

device: 'cuda:0'

3. 您的代码

from recbole.quick_start import run_recbole

config_dict = { 'device': 'cuda:0' # 或 'cpu',根据您的需求 }

run_recbole(model='DCN', dataset='ml-100k', config_file_list=['test.yaml'], config_dict=config_dict)


5. 您的运行脚本
直接运行即可
cywuuuu commented 3 days ago

请问这是否正常?还请问recbole支持对lightgcn求auc吗?谢谢 @Fotiligner