kn45 / ltr-dnn
LTR DNN in tensorflow, an improvement of DSSM
☆21Updated 6 years ago
Related projects: ⓘ
- Deep structured semantic model☆32Updated 8 years ago
- Learning Rank☆79Updated 7 years ago
- RankNet on TensorFlow☆21Updated 6 years ago
- ☆60Updated this week
- MXNet for CTR☆50Updated 7 years ago
- Multi-thread implementation of lambdaFM with FTRL for ranking problem. LambdaFM is a learning-to-rank algorithm by combining LambdaRank a…☆111Updated 3 years ago
- a improved dssm model for chinese or english☆25Updated 6 years ago
- spark-simrank scala☆17Updated 7 years ago
- using FM latent vectors as embedding features☆13Updated 7 years ago
- Deep Learning for Recommendation☆35Updated 7 years ago
- ☆91Updated 6 years ago
- This code is for Convolutional Latent Semantic Model, which is similay with DSSM(Deep Semantic Similarity Model).☆25Updated 9 years ago
- ☆20Updated this week
- ☆32Updated 6 years ago
- Distributed FM and LR based on Rabit with Lbfgs☆27Updated 8 years ago
- libffm with ftrl updater☆93Updated 7 years ago
- code exercise: dbscan(ballTree improve) | ctr(ftrl) | text classification(bayes..) | kmeans | general LR |..☆26Updated 8 years ago
- ☆22Updated 5 years ago
- ☆27Updated 7 years ago
- ☆31Updated 2 years ago
- items browsed in a session as a context are modeled to vec with bidirectional lstm☆18Updated 7 years ago
- A Tensorflow implementation of DSSM (slightly modified).☆25Updated 8 years ago
- Multi-thread implementation of Piece-wise Linear Model(PLM) or Mixture of LR(MLR) with FTRL for binary-class classification problem.☆127Updated 3 years ago
- ☆184Updated 7 years ago
- ☆59Updated this week
- Multi-thread implementation of Factorization Machines with FTRL for multi-class classification problem which uses softmax as hypothesis.☆70Updated 3 years ago
- pairwise learning to rank with logistic regression☆19Updated 8 years ago
- FFM implement with tensorflow by Python☆61Updated 6 years ago
- Keras (re)implementation of paper "Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks. SIGIR, 2015"☆68Updated 7 years ago