do you implement this paper LambdaFM: Learning Optimal Ranking with Factorization Machines Using Lambda Surrogates

CastellanZhang / lambdaFM

Multi-thread implementation of lambdaFM with FTRL for ranking problem. LambdaFM is a learning-to-rank algorithm by combining LambdaRank and Factorization Machines.

MIT License

111 stars 31 forks source link

do you implement this paper LambdaFM: Learning Optimal Ranking with Factorization Machines Using Lambda Surrogates #4

Open Sandy4321 opened 6 years ago

Sandy4321 commented 6 years ago

May you help understand what paper you use to this code? may be this one LambdaFM: Learning Optimal Ranking with Factorization Machines Using Lambda Surrogates

http://wnzhang.net/papers/lambdafm.pdf

CastellanZhang commented 6 years ago

Not this paper. The detail of my algorithm is here. It is a combination of LambdaRank and Factorization Machines.

CasyWang commented 6 years ago

The optimizer used in "LambdaFM: Learning Optimal Ranking with Factorization Machines Using Lambda Surrogates" is SGD, not follow the moving leader. Implementation of LambdaFM here is an online machine learning algorithm.