For more details, please take a look at our [examples](examples) as well as [tutorials](tutorials). For learning purposes, this list of [tutorials on recommender systems](https://github.com/PreferredAI/tutorials/tree/master/recommender-systems) will be more organized and comprehensive.
## Model serving
Here, we provide a simple way to serve a Cornac model by launching a standalone web service with [Flask](https://github.com/pallets/flask). It is very handy for testing or creating a demo application. First, we install the dependency:
...
...
@@ -130,84 +127,92 @@ If we want to remove seen items during training, we need to provide `TRAIN_SET`
## Efficient retrieval with ANN search
One important aspect of deploying recommender model is efficient retrieval via Approximate Nearest Neighor (ANN) search in vector space. Cornac integrates several vector similarity search frameworks for the ease of deployment. [This example](tutorials/ann_hnswlib.ipynb) demonstrates how ANN search will work seamlessly with any recommender models supporting it (e.g., MF).
One important aspect of deploying recommender model is efficient retrieval via Approximate Nearest Neighor (ANN) search in vector space. Cornac integrates several vector similarity search frameworks for the ease of deployment. [This example](tutorials/ann_hnswlib.ipynb) demonstrates how ANN search will work seamlessly with any recommender models supporting it (e.g., matrix factorization).
| | [Hybrid Deep Representation Learning of Ratings and Reviews (HRDR)](cornac/models/hrdr), [paper](https://www.sciencedirect.com/science/article/abs/pii/S0925231219313207) | Content-Based / Text | [reqs](cornac/models/hrdr/requirements.txt) | [exp](examples/hrdr_example.py)
| | [Learning to Rank Features for Recommendation over Multiple Categories (LRPPM)](cornac/models/lrppm), [paper](https://www.yongfeng.me/attach/sigir16-chen.pdf) | Explainable | N/A | [exp](examples/lrppm_example.py)
The table below lists the recommendation models/algorithms featured in Cornac. Examples are provided as quick-start showcasing an easy to run script, or as deep-dive explaining the math and intuition behind each model. Why don't you join us to lengthen the list?
| Year | Model and Paper | Type | Environment | Example |
| | [Hybrid Deep Representation Learning of Ratings and Reviews (HRDR)](cornac/models/hrdr), [paper](https://www.sciencedirect.com/science/article/abs/pii/S0925231219313207) | Content-Based / Text | [requirements](cornac/models/hrdr/requirements.txt), CPU / GPU | [quick-start](examples/hrdr_example.py)
| | [LightGCN: Simplifying and Powering Graph Convolution Network](cornac/models/lightgcn), [paper](https://arxiv.org/pdf/2002.02126.pdf) | Collaborative Filtering | [requirements](cornac/models/lightgcn/requirements.txt), CPU / GPU | [quick-start](examples/lightgcn_example.py)
| | [Predicting Temporal Sets with Deep Neural Networks (DNNTSP)](cornac/models/dnntsp), [paper](https://arxiv.org/pdf/2006.11483.pdf) | Next-Basket | [requirements](cornac/models/dnntsp/requirements.txt), CPU / GPU | [quick-start](examples/dnntsp_tafeng.py)
| | [Convolutional Matrix Factorization (ConvMF)](cornac/models/conv_mf), [paper](http://uclab.khu.ac.kr/resources/publication/C_351.pdf) | Content-Based / Text | [requirements](cornac/models/conv_mf/requirements.txt), CPU / GPU | [quick-start](examples/conv_mf_example.py), [deep-dive](https://github.com/PreferredAI/tutorials/blob/master/recommender-systems/09_deep_learning.ipynb)
| | [Learning to Rank Features for Recommendation over Multiple Categories (LRPPM)](cornac/models/lrppm), [paper](https://www.yongfeng.me/attach/sigir16-chen.pdf) | Explainable | CPU | [quick-start](examples/lrppm_example.py)
| | [Session-based Recommendations With Recurrent Neural Networks (GRU4Rec)](cornac/models/gru4rec), [paper](https://arxiv.org/pdf/1511.06939.pdf) | Next-Item | [requirements](cornac/models/gru4rec/requirements.txt), CPU / GPU | [quick-start](examples/gru4rec_yoochoose.py)
-[RecSys Tutorials by Preferred.AI](https://github.com/PreferredAI/tutorials/tree/master/recommender-systems)
-[Running Cornac Model with Microsoft Recommenders (BPR)](https://github.com/recommenders-team/recommenders/blob/main/examples/02_model_collaborative_filtering/cornac_bpr_deep_dive.ipynb), [(BiVAE)](https://github.com/recommenders-team/recommenders/blob/main/examples/02_model_collaborative_filtering/cornac_bivae_deep_dive.ipynb)
-[Multimodal RecSys Tutorial at TheWebConf/WWW 2023](https://github.com/PreferredAI/tutorials/blob/master/multimodal-www23/00_slides.pdf), [earlier version at RecSys 2021](https://github.com/PreferredAI/tutorials/blob/master/multimodal-recsys/slides.pdf)
## Contributing
...
...
@@ -218,7 +223,8 @@ This project welcomes contributions and suggestions. Before contributing, please
If you use Cornac in a scientific publication, we would appreciate citations to the following papers:
-[Cornac: A Comparative Framework for Multimodal Recommender Systems](http://jmlr.org/papers/v21/19-805.html), Salah *et al.*, Journal of Machine Learning Research, 21(95):1–5, 2020.
<details>
<summary><ahref="http://jmlr.org/papers/v21/19-805.html">Cornac: A Comparative Framework for Multimodal Recommender Systems</a>, Salah <i>et al.</i>, Journal of Machine Learning Research, 21(95):1–5, 2020.</summary>
```
@article{salah2020cornac,
...
...
@@ -231,8 +237,10 @@ If you use Cornac in a scientific publication, we would appreciate citations to
year={2020}
}
```
</details>
-[Exploring Cross-Modality Utilization in Recommender Systems](https://ieeexplore.ieee.org/abstract/document/9354572), Truong *et al.*, IEEE Internet Computing, 25(4):50–57, 2021.
<details>
<summary><ahref="https://ieeexplore.ieee.org/abstract/document/9354572">Exploring Cross-Modality Utilization in Recommender Systems</a>, Truong <i>et al.</i>, IEEE Internet Computing, 25(4):50–57, 2021.</summary>
```
@article{truong2021exploring,
...
...
@@ -243,8 +251,10 @@ If you use Cornac in a scientific publication, we would appreciate citations to
