Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

other parameters in Amazon dataset #10

Open
arnold-em opened this issue Mar 3, 2023 · 2 comments
Open

other parameters in Amazon dataset #10

arnold-em opened this issue Mar 3, 2023 · 2 comments

Comments

@arnold-em
Copy link

would you mind tell me other parameters setting
'Office_Products'
'Toys_and_Games'
'Digital_Music'
'Baby'
because the result is worse
这几个数据集的实验结果远远不如您们论文中的结果,我想问一下参数的设置

@arnold-em
Copy link
Author

validation: {'precision': array([0.00961979, 0.00192396, 0.00096198, 0.00048099, 0.00051535,
0.00041228, 0.00044282, 0.00047772, 0.000418 , 0.00039701,
0.00046267]), 'recall': array([0.00961979, 0.00961979, 0.00961979, 0.00961979, 0.02061383,
0.02061383, 0.02656894, 0.03344022, 0.03344022, 0.03573065,

0.04626661]), 'ndcg': array([0.00961979, 0.00961979, 0.00961979, 0.00961979, 0.01182631,
0.01182631, 0.01283418, 0.01398821, 0.01398821, 0.01434102,
0.01595609]), 'hit_ratio': array([0.00961979, 0.00961979, 0.00961979, 0.00961979, 0.02061383,
0.02061383, 0.02656894, 0.03344022, 0.03344022, 0.03573065,
0.04626661]), 'auc': 0.5943792945487865, 'mrr': 0.010333913727854603}
num_interactions: 984
test: {'precision': array([0.0101626 , 0.00203252, 0.00101626, 0.00050813, 0.0003811 ,
0.0003252 , 0.00032182, 0.0003194 , 0.00027947, 0.000271 ,
0.00028455]), 'recall': array([0.0101626 , 0.0101626 , 0.0101626 , 0.0101626 , 0.0152439 ,
0.01626016, 0.01930894, 0.02235772, 0.02235772, 0.02439024,

0.02845528]), 'ndcg': array([0.0101626 , 0.0101626 , 0.0101626 , 0.0101626 , 0.01118262,
0.01136178, 0.01187937, 0.01239141, 0.01239141, 0.01270411,
0.01332725]), 'hit_ratio': array([0.0101626 , 0.0101626 , 0.0101626 , 0.0101626 , 0.0152439 ,
0.01626016, 0.01930894, 0.02235772, 0.02235772, 0.02439024,
0.02845528]), 'auc': 0.5647052845528463, 'mrr': 0.010518675003895705}
in digital music ,the result is the worse in other baseline ,i dont know what wrong

@siddhantpathakk
Copy link

May I ask if you used 2014 dataset or something different?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants