How to test this algorithm on other data sets such as ml-1m? about sigir16-eals HOT 6 CLOSED

On Tue, Aug 7, 2018 at 9:39 AM, Dengzhh ***@***.***> wrote: Hi, Professor He. Recently I'm trying to test e-als on ml-1m and some other data sets, but I'm not so familiar with programming with JAVA. I've preprocessed the data sets in the same form as you shown in the yelp data set. However, without any modification, when I run main_MF.java to test the offline performance, I got an extremely bad result, i.e., 0.4xxx for HR and 0.01xx for NDCG. This is unacceptable since a simple MF algorithm can have much better performance. Do you have any suggestion about how to reproduce your results? (ml-1m is tested in your paper "Neural Collaborative Filtering" but I can't reproduce the same results) Or do I need to modify some critical parameters? Thanks. Here is the parameters I used: Data data/ml-1m.rating #Users 6040 #Items 3706 #Ratings 994169 (train), 6040(test) FastALS: showProgress=false, factors=64, maxIter=500, reg=0.010000, w0=10.00, alpha=0.75 — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#2>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ABGxjoi_YLB6NYYtmEV6_BmKqoPZ7Ik0ks5uOO_EgaJpZM4VxV_1> .

On Wed, Aug 8, 2018 at 5:48 PM, Dengzhh ***@***.***> wrote: @hexiangnan <https://github.com/hexiangnan> Hi, Professor He. I've rewritten the code to test eALS in the same way as you mentioned in the NCF paper, i.e., ranks 99 sampled negatives + 1 positive item. Besides, I use ml-1m.train.rating & ml-1m.test.rating & ml-1m.test.negative， which you provided in the neural_collaborative_filtering project. However, the performance of eALS is still not satisfying. For top-10 recommendation, the best iteration among 50 iterations yields <iter, hr, ndcg, prec>: 16 0.6078 0.3411 0.2594, which is much lower than what you presented in the NCF paper. The parameter settings is unchanged as: Data ml-1m #Users 6040 #Items 3706 #Ratings 994169 (train), 6040(testPositive), 6040(testNegative) fastALS: showProgress=false, factors=64, maxIter=50, reg=0.010000, w0=10.00, alpha=0.75 Do you have any suggestions to reproduce the results shown in the NCF paper? Thank you for taking your precious time to read this. Your prompt reply will be highly appreciated. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#2 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ABGxjvJYgfhB-CO_HiY4fCyq_T9_3BILks5uOrPvgaJpZM4VxV_1> .