linzh92 / Deepicf
Licence: other
TensorFlow Implementation of Deep Item-based Collaborative Filtering Model for Top-N Recommendation
Stars: ✭ 86
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Deepicf
Cnn Paper2
🎨 🎨 深度学习 卷积神经网络教程 ：图像识别，目标检测，语义分割，实例分割，人脸识别，神经风格转换，GAN等🎨🎨 https://dataxujing.github.io/CNN-paper2/
Stars: ✭ 77 (-10.47%)
Mutual labels: deep-neural-networks
Graphmat
GraphMat graph analytics framework
Stars: ✭ 81 (-5.81%)
Mutual labels: collaborative-filtering
Cfsrcnn
Coarse-to-Fine CNN for Image Super-Resolution (IEEE Transactions on Multimedia,2020)
Stars: ✭ 84 (-2.33%)
Mutual labels: deep-neural-networks
Awesome Learning With Label Noise
A curated list of resources for Learning with Noisy Labels
Stars: ✭ 1,205 (+1301.16%)
Mutual labels: deep-neural-networks
Flops Counter.pytorch
Flops counter for convolutional networks in pytorch framework
Stars: ✭ 1,223 (+1322.09%)
Mutual labels: deep-neural-networks
Forge
A neural network toolkit for Metal
Stars: ✭ 1,242 (+1344.19%)
Mutual labels: deep-neural-networks
Swae
Implementation of the Sliced Wasserstein Autoencoders
Stars: ✭ 75 (-12.79%)
Mutual labels: deep-neural-networks
Breast Cancer Classification
Breast Cancer Classification using CNN and transfer learning
Stars: ✭ 86 (+0%)
Mutual labels: deep-neural-networks
Adn
ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction
Stars: ✭ 81 (-5.81%)
Mutual labels: deep-neural-networks
X Ray Classification
X-ray Images (Chest images) analysis and anomaly detection using Transfer learning with inception v2
Stars: ✭ 83 (-3.49%)
Mutual labels: deep-neural-networks
Sdtw pytorch
Implementation of soft dynamic time warping in pytorch
Stars: ✭ 79 (-8.14%)
Mutual labels: deep-neural-networks
Torch Encoding Layer
Deep Texture Encoding Network
Stars: ✭ 80 (-6.98%)
Mutual labels: deep-neural-networks
Neural collaborative filtering
Neural Collaborative Filtering
Stars: ✭ 1,243 (+1345.35%)
Mutual labels: collaborative-filtering
Anrl
ANRL: Attributed Network Representation Learning via Deep Neural Networks(IJCAI-2018)
Stars: ✭ 77 (-10.47%)
Mutual labels: deep-neural-networks
Deepsequenceclassification
Deep neural network based model for sequence to sequence classification
Stars: ✭ 76 (-11.63%)
Mutual labels: deep-neural-networks
Niftynet
[unmaintained] An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy
Stars: ✭ 1,276 (+1383.72%)
Mutual labels: deep-neural-networks
Movie Recommender System
Basic Movie Recommendation Web Application using user-item collaborative filtering.
Stars: ✭ 85 (-1.16%)
Mutual labels: collaborative-filtering
Dltk
Deep Learning Toolkit for Medical Image Analysis
Stars: ✭ 1,249 (+1352.33%)
Mutual labels: deep-neural-networks
DeepICF
TensorFlow Implementation of Deep Item-based Collaborative Filtering Model for Top-N Recommendation
This is the official implementation for the paper as follows, which is based on the implementation of NAIS (TKDE 2018):
- Feng Xue, Xiangnan He, Xiang Wang, Jiandong Xu, Kai Liu, Richang Hong, Deep Item-based Collaborative Filtering for Top-N Recommendation. ACM Trans. Inf. Syst. 37(3): 33:1-33:25 (2019)
Two deep collaborative filtering models: DeepICF & DeepICF+a. To target the models for implicit feedback and ranking task, we optimize them using log loss with negative sampling.
Please cite our paper if you use our codes. Thx!
Environment Settings
- Python: '2.7'
- TensorFlow: 'r1.0'
- Numpy: '1.13'
Examples to run the codes
Run DeepICF (with FISM item embeddings pre-training):
python DeepICF.py --path Data/ --dataset ml-1m --epochs 100 --verbose 1 --batch_choice user --embed_size 16 --layers [64,32,16] --regs [1e-06,1e-06] --reg_W [0.1,0.1,0.1,0.1] --alpha 0.5 --train_loss 1 --num_neg 4 --lr 0.01 --batch_norm 1 --pretrain 1
Output of DeepICF:
...
Run DeepICF+a (with FISM item embeddings pre-training):
python DeepICF_a.py --path Data/ --dataset ml-1m --epochs 100 --beta 0.8 --weight_size 16 --activation 0 --algorithm 0 --verbose 1 --batch_choice user --embed_size 16 --layers [64,32,16] --regs [1e-06,1e-06,1e-06] --reg_W [10,10,10,10] --alpha 0 --train_loss 1 --num_neg 4 --lr 0.01 --batch_norm 1 --pretrain 1
Output of DeepICF+a:
...
Datasets
We provide two processed datasets: MovieLens 1 Million (ml-1m) and Pinterest (pinterest-20).
train.rating:
- Train file.
- Each Line is a training instance: userID\t itemID\t rating\t timestamp (if have)
test.rating:
- Test file (positive instances).
- Each Line is a testing instance: userID\t itemID\t rating\t timestamp (if have)
test.negative:
- Test file (negative instances).
- Each line corresponds to the line of test.rating, containing 99 negative samples.
- Each line is in the format: (userID,itemID)\t negativeItemID1\t negativeItemID2 ...
Update Date: Feb 23, 2019
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].