diff --git a/docs/generate_model_js.py b/docs/generate_model_js.py
new file mode 100644
index 0000000000000000000000000000000000000000..ba894314ebb0ffda9400f91e38ed0b36b969e71f
--- /dev/null
+++ b/docs/generate_model_js.py
@@ -0,0 +1,101 @@
+import json
+
+
+def get_key_val(part):
+ key_index_start = part.index('[')
+ key_index_end = part.index(']')
+ val_index_start = part.rindex('(')
+ val_index_end = part.rindex(')')
+
+ key = part[key_index_start + 1: key_index_end]
+ val = part[val_index_start + 1: val_index_end]
+
+ return key, val
+
+
+# Read the content from README.md
+with open('../README.md', 'r') as file:
+ content = file.read()
+
+# Extract the relevant information from the content
+models = []
+lines = content.split('\n')
+lines = lines[lines.index('## Models') + 4: lines.index('## Resources') - 2]
+
+headers = []
+headers = lines[0].split('|')[1:-1]
+headers = [header.strip() for header in headers]
+
+for line in lines[2:]:
+ parts = line.split('|')[1:-1]
+ parts = [part.strip() for part in parts]
+ model = dict(zip(headers, parts))
+ models.append(model)
+
+year = None
+
+for model in models:
+ # handle empty years
+ if model["Year"] == "":
+ model["Year"] = year
+ else:
+ year = model["Year"]
+
+ # handle model, docs and paper part
+ name_paper_str = model["Model and Paper"]
+
+ for i, part in enumerate(name_paper_str.split(', ')):
+ key, val = get_key_val(part)
+
+ if i == 0:
+ model["Name"] = key
+ model["Link"] = val
+ else:
+ model[key] = val
+
+ # handle environment part
+
+ env_part = model["Environment"].split(', ')[0]
+
+ search_dict = {
+ "PyTorch": "torch",
+ "TensorFlow": "tensorflow"
+ }
+
+ if "requirements" in env_part:
+ _, requirements_dir = get_key_val(env_part)
+
+ # read requirements file
+ with open(f'../{requirements_dir}', 'r') as file:
+ requirements = file.read()
+
+ for header, package in search_dict.items():
+ model[header] = package in requirements
+ else:
+ for header, _ in search_dict.items():
+ model[header] = False
+
+ # remove non required keys
+ model.pop("Model and Paper")
+ model.pop("Environment")
+
+ # Get package name
+ model_dir = model["Link"]
+
+ with open(f'../{model_dir}/__init__.py', 'r') as file:
+ init_data = file.read()
+
+ package_names = []
+
+ for row in init_data.split('\n'):
+ if "import" in row:
+ package_name = row[row.index("import") + len("import "):]
+ package_names.append(f"cornac.models.{package_name}")
+
+ model["packages"] = package_names
+
+json_str = json.dumps(models, indent=4)
+
+# Write the JSON object to a file
+with open('source/_static/models/data.js', 'w') as file:
+ file.write(f"var data = {json_str};")
diff --git a/docs/source/_static/models/data.js b/docs/source/_static/models/data.js
new file mode 100644
index 0000000000000000000000000000000000000000..678a72bb096790f284ae18512d45b47049504d57
--- /dev/null
+++ b/docs/source/_static/models/data.js
@@ -0,0 +1,804 @@
+var data = [
+ {
+ "Year": "2024",
+ "Type": "Hybrid / Sentiment / Explainable",
+ "Name": "Hypergraphs with Attention on Reviews (HypAR)",
+ "Link": "cornac/models/hypar",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.hypar.recom_hypar",
+ "paper": "https://doi.org/10.1007/978-3-031-56027-9_14",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.HypAR"
+ ]
+ },
+ {
+ "Year": "2022",
+ "Type": "Content-Based / Text & Image",
+ "Name": "Disentangled Multimodal Representation Learning for Recommendation (DMRL)",
+ "Link": "cornac/models/dmrl",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.dmrl.recom_dmrl",
+ "paper": "https://arxiv.org/pdf/2203.05406.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.DMRL"
+ ]
+ },
+ {
+ "Year": "2021",
+ "Type": "Collaborative Filtering / Content-Based",
+ "Name": "Bilateral Variational Autoencoder for Collaborative Filtering (BiVAECF)",
+ "Link": "cornac/models/bivaecf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.bivaecf.recom_bivaecf",
+ "paper": "https://dl.acm.org/doi/pdf/10.1145/3437963.3441759",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.BiVAECF"
+ ]
+ },
+ {
+ "Year": "2021",
+ "Type": "Content-Based / Image",
+ "Name": "Causal Inference for Visual Debiasing in Visually-Aware Recommendation (CausalRec)",
+ "Link": "cornac/models/causalrec",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.causalrec.recom_causalrec",
+ "paper": "https://arxiv.org/abs/2107.02390",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.CausalRec"
+ ]
+ },
+ {
+ "Year": "2021",
+ "Type": "Explainable",
+ "Name": "Explainable Recommendation with Comparative Constraints on Product Aspects (ComparER)",
+ "Link": "cornac/models/comparer",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.comparer.recom_comparer_sub",
+ "paper": "https://dl.acm.org/doi/pdf/10.1145/3437963.3441754",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.ComparERSub",
+ "cornac.models.ComparERObj"
+ ]
+ },
+ {
+ "Year": "2020",
+ "Type": "Content-Based / Image",
+ "Name": "Adversarial Multimedia Recommendation (AMR)",
+ "Link": "cornac/models/amr",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.amr.recom_amr",
+ "paper": "https://ieeexplore.ieee.org/document/8618394",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.AMR"
+ ]
+ },
+ {
+ "Year": "2020",
+ "Type": "Content-Based / Text",
+ "Name": "Hybrid Deep Representation Learning of Ratings and Reviews (HRDR)",
+ "Link": "cornac/models/hrdr",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.hrdr.recom_hrdr",
+ "paper": "https://www.sciencedirect.com/science/article/abs/pii/S0925231219313207",
+ "PyTorch": false,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.HRDR"
+ ]
+ },
+ {
+ "Year": "2020",
+ "Type": "Collaborative Filtering",
+ "Name": "LightGCN: Simplifying and Powering Graph Convolution Network",
+ "Link": "cornac/models/lightgcn",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.lightgcn.recom_lightgcn",
+ "paper": "https://arxiv.org/pdf/2002.02126.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.LightGCN"
+ ]
+ },
+ {
+ "Year": "2020",
+ "Type": "Next-Basket",
+ "Name": "Predicting Temporal Sets with Deep Neural Networks (DNNTSP)",
+ "Link": "cornac/models/dnntsp",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.dnntsp.recom_dnntsp",
+ "paper": "https://arxiv.org/pdf/2006.11483.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.DNNTSP"
+ ]
+ },
+ {
+ "Year": "2020",
+ "Type": "Next-Basket",
+ "Name": "Recency Aware Collaborative Filtering (UPCF)",
+ "Link": "cornac/models/upcf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.upcf.recom_upcf",
+ "paper": "https://dl.acm.org/doi/abs/10.1145/3340631.3394850",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.UPCF"
+ ]
+ },
+ {
+ "Year": "2020",
+ "Type": "Next-Basket",
+ "Name": "Temporal-Item-Frequency-based User-KNN (TIFUKNN)",
+ "Link": "cornac/models/tifuknn",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.tifuknn.recom_tifuknn",
+ "paper": "https://arxiv.org/pdf/2006.00556.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.TIFUKNN"
+ ]
+ },
+ {
+ "Year": "2020",
+ "Type": "Collaborative Filtering",
+ "Name": "Variational Autoencoder for Top-N Recommendations (RecVAE)",
+ "Link": "cornac/models/recvae",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.recvae.recom_recvae",
+ "paper": "https://doi.org/10.1145/3336191.3371831",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.RecVAE"
+ ]
+ },
+ {
+ "Year": "2019",
+ "Type": "Next-Basket",
+ "Name": "Correlation-Sensitive Next-Basket Recommendation (Beacon)",
+ "Link": "cornac/models/beacon",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#correlation-sensitive-next-basket-recommendation-beacon",
+ "paper": "https://www.ijcai.org/proceedings/2019/0389.pdf",
+ "PyTorch": false,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.Beacon"
+ ]
+ },
+ {
+ "Year": "2019",
+ "Type": "Collaborative Filtering",
+ "Name": "Embarrassingly Shallow Autoencoders for Sparse Data (EASE\u1d3f)",
+ "Link": "cornac/models/ease",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.ease.recom_ease",
+ "paper": "https://arxiv.org/pdf/1905.03375.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.EASE"
+ ]
+ },
+ {
+ "Year": "2019",
+ "Type": "Collaborative Filtering",
+ "Name": "Neural Graph Collaborative Filtering (NGCF)",
+ "Link": "cornac/models/ngcf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.ngcf.recom_ngcf",
+ "paper": "https://arxiv.org/pdf/1905.08108.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.NGCF"
+ ]
+ },
+ {
+ "Year": "2018",
+ "Type": "Content-Based / Graph",
+ "Name": "Collaborative Context Poisson Factorization (C2PF)",
+ "Link": "cornac/models/c2pf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.c2pf.recom_c2pf",
+ "paper": "https://www.ijcai.org/proceedings/2018/0370.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.C2PF"
+ ]
+ },
+ {
+ "Year": "2018",
+ "Type": "Collaborative Filtering",
+ "Name": "Graph Convolutional Matrix Completion (GCMC)",
+ "Link": "cornac/models/gcmc",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.gcmc.recom_gcmc",
+ "paper": "https://www.kdd.org/kdd2018/files/deep-learning-day/DLDay18_paper_32.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.GCMC"
+ ]
+ },
+ {
+ "Year": "2018",
+ "Type": "Explainable",
+ "Name": "Multi-Task Explainable Recommendation (MTER)",
+ "Link": "cornac/models/mter",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.mter.recom_mter",
+ "paper": "https://arxiv.org/pdf/1806.03568.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.MTER"
+ ]
+ },
+ {
+ "Year": "2018",
+ "Type": "Explainable / Content-Based",
+ "Name": "Neural Attention Rating Regression with Review-level Explanations (NARRE)",
+ "Link": "cornac/models/narre",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.narre.recom_narre",
+ "paper": "http://www.thuir.cn/group/~YQLiu/publications/WWW2018_CC.pdf",
+ "PyTorch": false,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.NARRE"
+ ]
+ },
+ {
+ "Year": "2018",
+ "Type": "Content-Based / Graph",
+ "Name": "Probabilistic Collaborative Representation Learning (PCRL)",
+ "Link": "cornac/models/pcrl",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.pcrl.recom_pcrl",
+ "paper": "http://www.hadylauw.com/publications/uai18.pdf",
+ "PyTorch": false,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.PCRL"
+ ]
+ },
+ {
+ "Year": "2018",
+ "Type": "Collaborative Filtering",
+ "Name": "Variational Autoencoder for Collaborative Filtering (VAECF)",
+ "Link": "cornac/models/vaecf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.vaecf.recom_vaecf",
+ "paper": "https://arxiv.org/pdf/1802.05814.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.VAECF"
+ ]
+ },
+ {
+ "Year": "2017",
+ "Type": "Content-Based / Text",
+ "Name": "Collaborative Variational Autoencoder (CVAE)",
+ "Link": "cornac/models/cvae",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.cvae.recom_cvae",
+ "paper": "http://eelxpeng.github.io/assets/paper/Collaborative_Variational_Autoencoder.pdf",
+ "PyTorch": false,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.CVAE"
+ ]
+ },
+ {
+ "Year": "2017",
+ "Type": "Content-Based / Text",
+ "Name": "Conditional Variational Autoencoder for Collaborative Filtering (CVAECF)",
+ "Link": "cornac/models/cvaecf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.cvaecf.recom_cvaecf",
+ "paper": "https://dl.acm.org/doi/10.1145/3132847.3132972",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.CVAECF"
+ ]
+ },
+ {
+ "Year": "2017",
+ "Type": "Collaborative Filtering",
+ "Name": "Generalized Matrix Factorization (GMF)",
+ "Link": "cornac/models/ncf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.ncf.recom_gmf",
+ "paper": "https://arxiv.org/pdf/1708.05031.pdf",
+ "PyTorch": true,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.GMF",
+ "cornac.models.MLP",
+ "cornac.models.NeuMF"
+ ]
+ },
+ {
+ "Year": "2017",
+ "Type": "Collaborative Filtering",
+ "Name": "Indexable Bayesian Personalized Ranking (IBPR)",
+ "Link": "cornac/models/ibpr",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.ibpr.recom_ibpr",
+ "paper": "http://www.hadylauw.com/publications/cikm17a.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.IBPR"
+ ]
+ },
+ {
+ "Year": "2017",
+ "Type": "Content-Based / Graph",
+ "Name": "Matrix Co-Factorization (MCF)",
+ "Link": "cornac/models/mcf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.mcf.recom_mcf",
+ "paper": "https://dsail.kaist.ac.kr/files/WWW17.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.MCF"
+ ]
+ },
+ {
+ "Year": "2017",
+ "Type": "Collaborative Filtering",
+ "Name": "Multi-Layer Perceptron (MLP)",
+ "Link": "cornac/models/ncf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.ncf.recom_mlp",
+ "paper": "https://arxiv.org/pdf/1708.05031.pdf",
+ "PyTorch": true,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.GMF",
+ "cornac.models.MLP",
+ "cornac.models.NeuMF"
+ ]
+ },
+ {
+ "Year": "2017",
+ "Type": "Collaborative Filtering",
+ "Name": "Neural Matrix Factorization (NeuMF) / Neural Collaborative Filtering (NCF)",
+ "Link": "cornac/models/ncf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.ncf.recom_neumf",
+ "paper": "https://arxiv.org/pdf/1708.05031.pdf",
+ "PyTorch": true,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.GMF",
+ "cornac.models.MLP",
+ "cornac.models.NeuMF"
+ ]
+ },
+ {
+ "Year": "2017",
+ "Type": "Collaborative Filtering",
+ "Name": "Online Indexable Bayesian Personalized Ranking (Online IBPR)",
+ "Link": "cornac/models/online_ibpr",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.online_ibpr.recom_online_ibpr",
+ "paper": "http://www.hadylauw.com/publications/cikm17a.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.OnlineIBPR"
+ ]
+ },
+ {
+ "Year": "2017",
+ "Type": "Content-Based / Image",
+ "Name": "Visual Matrix Factorization (VMF)",
+ "Link": "cornac/models/vmf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.vmf.recom_vmf",
+ "paper": "https://dsail.kaist.ac.kr/files/WWW17.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.VMF"
+ ]
+ },
+ {
+ "Year": "2016",
+ "Type": "Content-Based / Text",
+ "Name": "Collaborative Deep Ranking (CDR)",
+ "Link": "cornac/models/cdr",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.cdr.recom_cdr",
+ "paper": "http://inpluslab.com/chenliang/homepagefiles/paper/hao-pakdd2016.pdf",
+ "PyTorch": false,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.CDR"
+ ]
+ },
+ {
+ "Year": "2016",
+ "Type": "Collaborative Filtering",
+ "Name": "Collaborative Ordinal Embedding (COE)",
+ "Link": "cornac/models/coe",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.coe.recom_coe",
+ "paper": "http://www.hadylauw.com/publications/sdm16.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.COE"
+ ]
+ },
+ {
+ "Year": "2016",
+ "Type": "Content-Based / Text",
+ "Name": "Convolutional Matrix Factorization (ConvMF)",
+ "Link": "cornac/models/conv_mf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.conv_mf.recom_convmf",
+ "paper": "http://uclab.khu.ac.kr/resources/publication/C_351.pdf",
+ "PyTorch": false,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.ConvMF"
+ ]
+ },
+ {
+ "Year": "2016",
+ "Type": "Explainable",
+ "Name": "Learning to Rank Features for Recommendation over Multiple Categories (LRPPM)",
+ "Link": "cornac/models/lrppm",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#learn-to-rank-user-preferences-based-on-phrase-level-sentiment-analysis-across-multiple-categories-lrppm",
+ "paper": "https://www.yongfeng.me/attach/sigir16-chen.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.LRPPM"
+ ]
+ },
+ {
+ "Year": "2016",
+ "Type": "Next-Item",
+ "Name": "Session-based Recommendations With Recurrent Neural Networks (GRU4Rec)",
+ "Link": "cornac/models/gru4rec",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.gru4rec.recom_gru4rec",
+ "paper": "https://arxiv.org/pdf/1511.06939.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.GRU4Rec"
+ ]
+ },
+ {
+ "Year": "2016",
+ "Type": "Collaborative Filtering",
+ "Name": "Spherical K-means (SKM)",
+ "Link": "cornac/models/skm",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.skm.recom_skmeans",
+ "paper": "https://www.sciencedirect.com/science/article/pii/S092523121501509X",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.SKMeans"
+ ]
+ },
+ {
+ "Year": "2016",
+ "Type": "Content-Based / Image",
+ "Name": "Visual Bayesian Personalized Ranking (VBPR)",
+ "Link": "cornac/models/vbpr",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.vbpr.recom_vbpr",
+ "paper": "https://arxiv.org/pdf/1510.01784.pdf",
+ "PyTorch": true,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.VBPR"
+ ]
+ },
+ {
+ "Year": "2015",
+ "Type": "Content-Based / Text",
+ "Name": "Collaborative Deep Learning (CDL)",
+ "Link": "cornac/models/cdl",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.cdl.recom_cdl",
+ "paper": "https://arxiv.org/pdf/1409.2944.pdf",
+ "PyTorch": false,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.CDL"
+ ]
+ },
+ {
+ "Year": "2015",
+ "Type": "Collaborative Filtering",
+ "Name": "Hierarchical Poisson Factorization (HPF)",
+ "Link": "cornac/models/hpf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.hpf.recom_hpf",
+ "paper": "http://jakehofman.com/inprint/poisson_recs.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.HPF"
+ ]
+ },
+ {
+ "Year": "2015",
+ "Type": "Explainable",
+ "Name": "TriRank: Review-aware Explainable Recommendation by Modeling Aspects",
+ "Link": "cornac/models/trirank",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.trirank.recom_trirank",
+ "paper": "https://wing.comp.nus.edu.sg/wp-content/uploads/Publications/PDF/TriRank-%20Review-aware%20Explainable%20Recommendation%20by%20Modeling%20Aspects.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.TriRank"
+ ]
+ },
+ {
+ "Year": "2014",
+ "Type": "Explainable",
+ "Name": "Explicit Factor Model (EFM)",
+ "Link": "cornac/models/efm",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.efm.recom_efm",
+ "paper": "https://www.yongfeng.me/attach/efm-zhang.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.EFM"
+ ]
+ },
+ {
+ "Year": "2014",
+ "Type": "Content-Based / Social",
+ "Name": "Social Bayesian Personalized Ranking (SBPR)",
+ "Link": "cornac/models/sbpr",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#social-bayesian-personalized-ranking-sbpr",
+ "paper": "https://cseweb.ucsd.edu/~jmcauley/pdfs/cikm14.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.SBPR"
+ ]
+ },
+ {
+ "Year": "2013",
+ "Type": "Content-Based / Text",
+ "Name": "Hidden Factors and Hidden Topics (HFT)",
+ "Link": "cornac/models/hft",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.hft.recom_hft",
+ "paper": "https://cs.stanford.edu/people/jure/pubs/reviews-recsys13.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.HFT"
+ ]
+ },
+ {
+ "Year": "2012",
+ "Type": "Collaborative Filtering",
+ "Name": "Weighted Bayesian Personalized Ranking (WBPR)",
+ "Link": "cornac/models/bpr",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#weighted-bayesian-personalized-ranking-wbpr",
+ "paper": "http://proceedings.mlr.press/v18/gantner12a/gantner12a.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.BPR",
+ "cornac.models.WBPR"
+ ]
+ },
+ {
+ "Year": "2011",
+ "Type": "Content-Based / Text",
+ "Name": "Collaborative Topic Regression (CTR)",
+ "Link": "cornac/models/ctr",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.ctr.recom_ctr",
+ "paper": "http://www.cs.columbia.edu/~blei/papers/WangBlei2011.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.CTR"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Baseline",
+ "Name": "Baseline Only",
+ "Link": "cornac/models/baseline_only",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#baseline-only",
+ "paper": "http://courses.ischool.berkeley.edu/i290-dm/s11/SECURE/a1-koren.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.BaselineOnly"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Collaborative Filtering",
+ "Name": "Bayesian Personalized Ranking (BPR)",
+ "Link": "cornac/models/bpr",
+ "docs": "https://arxiv.org/ftp/arxiv/papers/1205/1205.2618.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.BPR",
+ "cornac.models.WBPR"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Collaborative Filtering / Content-Based",
+ "Name": "Factorization Machines (FM)",
+ "Link": "cornac/models/fm",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#factorization-machines-fm",
+ "paper": "https://www.csie.ntu.edu.tw/~b97053/paper/Factorization%20Machines%20with%20libFM.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.FM"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Baseline",
+ "Name": "Global Average (GlobalAvg)",
+ "Link": "cornac/models/global_avg",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.global_avg.recom_global_avg",
+ "paper": "https://datajobs.com/data-science-repo/Recommender-Systems-[Netflix].pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.GlobalAvg"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Next-Basket",
+ "Name": "Global Personalized Top Frequent (GPTop)",
+ "Link": "cornac/models/gp_top",
+ "paper": "https://dl.acm.org/doi/pdf/10.1145/3587153",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.GPTop"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Neighborhood-Based",
+ "Name": "Item K-Nearest-Neighbors (ItemKNN)",
+ "Link": "cornac/models/knn",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#item-k-nearest-neighbors-itemknn",
+ "paper": "https://dl.acm.org/doi/pdf/10.1145/371920.372071",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.ItemKNN",
+ "cornac.models.UserKNN"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Collaborative Filtering",
+ "Name": "Matrix Factorization (MF)",
+ "Link": "cornac/models/mf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.mf.recom_mf",
+ "paper": "https://datajobs.com/data-science-repo/Recommender-Systems-[Netflix].pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.MF"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Collaborative Filtering",
+ "Name": "Maximum Margin Matrix Factorization (MMMF)",
+ "Link": "cornac/models/mmmf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.mmmf.recom_mmmf",
+ "paper": "https://link.springer.com/content/pdf/10.1007/s10994-008-5073-7.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.MMMF"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Baseline",
+ "Name": "Most Popular (MostPop)",
+ "Link": "cornac/models/most_pop",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.most_pop.recom_most_pop",
+ "paper": "https://arxiv.org/ftp/arxiv/papers/1205/1205.2618.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.MostPop"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Collaborative Filtering",
+ "Name": "Non-negative Matrix Factorization (NMF)",
+ "Link": "cornac/models/nmf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.nmf.recom_nmf",
+ "paper": "http://papers.nips.cc/paper/1861-algorithms-for-non-negative-matrix-factorization.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.NMF"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Collaborative Filtering",
+ "Name": "Probabilistic Matrix Factorization (PMF)",
+ "Link": "cornac/models/pmf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.pmf.recom_pmf",
+ "paper": "https://papers.nips.cc/paper/3208-probabilistic-matrix-factorization.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.PMF"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Next-Item / Baseline",
+ "Name": "Session Popular (SPop)",
+ "Link": "cornac/models/spop",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.spop.recom_spop",
+ "paper": "https://arxiv.org/pdf/1511.06939.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.SPop"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Collaborative Filtering",
+ "Name": "Singular Value Decomposition (SVD)",
+ "Link": "cornac/models/svd",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.svd.recom_svd",
+ "paper": "https://people.engr.tamu.edu/huangrh/Spring16/papers_course/matrix_factorization.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.SVD"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Content-Based / Social",
+ "Name": "Social Recommendation using PMF (SoRec)",
+ "Link": "cornac/models/sorec",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.sorec.recom_sorec",
+ "paper": "http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.304.2464&rep=rep1&type=pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.SoRec"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Neighborhood-Based",
+ "Name": "User K-Nearest-Neighbors (UserKNN)",
+ "Link": "cornac/models/knn",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#user-k-nearest-neighbors-userknn",
+ "paper": "https://arxiv.org/pdf/1301.7363.pdf",
+ "PyTorch": false,
+ "TensorFlow": false,
+ "packages": [
+ "cornac.models.ItemKNN",
+ "cornac.models.UserKNN"
+ ]
+ },
+ {
+ "Year": "Earlier",
+ "Type": "Collaborative Filtering",
+ "Name": "Weighted Matrix Factorization (WMF)",
+ "Link": "cornac/models/wmf",
+ "docs": "https://cornac.readthedocs.io/en/stable/api_ref/models.html#module-cornac.models.wmf.recom_wmf",
+ "paper": "http://yifanhu.net/PUB/cf.pdf",
+ "PyTorch": false,
+ "TensorFlow": true,
+ "packages": [
+ "cornac.models.WMF"
+ ]
+ }
+];
\ No newline at end of file
diff --git a/docs/source/_static/models/models.html b/docs/source/_static/models/models.html
new file mode 100644
index 0000000000000000000000000000000000000000..fcee3e469d19c12cd6d2c6a0f9bff7258e29699b
--- /dev/null
+++ b/docs/source/_static/models/models.html
@@ -0,0 +1,104 @@
+<html lang="en">
+ <head>
+ <script src="https://cdn.jsdelivr.net/npm/ag-grid-community/dist/ag-grid-community.min.js"></script>
+ </head>
+ <body>
+ <h3>Filters</h3>
+ <div>
+ <button onclick="clearFilters()">Clear Filters</button>
+ </div>
+ <div style="margin-top: 16px;">
+ <button onclick="filterModels('Collaborative Filtering')">Collaborative Filtering Models</button>
+ <button onclick="filterModels('Content-Based')">Content Based Models</button>
+ <button onclick="filterModels('Explainable')">Explainable Models</button>
+ <button onclick="filterModels('Next-Item')">Next-Item Models</button>
+ <button onclick="filterModels('Next-Basket')">Next-Basket Models</button>
+ <button onclick="filterModels('Baseline')">Baseline Models</button>
+ </div>
+ <div style="margin-top: 16px;">
+ <input type="text" id="filter-text-box" size="50" placeholder="Fliter" oninput="onFilterTextBoxChanged()" />
+ </div>
+ <br />
+ <div id="grid" class="ag-theme-quartz" style="height: 480px"></div>
+ </body>
+</html>
+<script type="text/javascript" src="data.js"></script>
+<script type="text/javascript" src="_static/models/data.js"></script>
+<script type="text/javascript">
+ function LinkRenderer(url, title) {
+ return `<a href="${url}" target="_blank">${title}</a>`
+ }
+ // Row Data Interface
+ const github_url = "https://github.com/PreferredAI/cornac/tree/master/";
+
+ // Grid API: Access to Grid API methods
+ let gridApi;
+
+ function onFilterTextBoxChanged() {
+ gridApi.setGridOption(
+ "quickFilterText",
+ document.getElementById("filter-text-box").value,
+ );
+ }
+
+ function filterModels(filter) {
+ gridApi.setColumnFilterModel("Type", {
+ type: "contains",
+ filter: filter,
+ })
+ .then(() => {
+ gridApi.onFilterChanged();
+ });
+ }
+
+ function clearFilters(){
+ gridApi.setColumnFilterModel("Type", null)
+ .then(() => {
+ gridApi.onFilterChanged();
+ });
+ // reset filter box
+ document.getElementById("filter-text-box").value="";
+ gridApi.setGridOption(
+ "quickFilterText",
+ "",
+ );
+ }
+
+ // Grid Options: Contains all of the grid configurations
+ const gridOptions = {
+ // Data to be displayed
+ rowData: data,
+ // Columns to be displayed (Should match rowData properties)
+ columnDefs: [
+ { field: "Year" },
+ {
+ field: "Name",
+ headerName: "Model Name (Hover over for package name)",
+
+ flex: 4,
+ cellRenderer: params => LinkRenderer(params.data.docs, params.data.Name),
+ tooltipValueGetter: (params) => "Package Name: " + params.data.packages,
+ },
+ { field: "Type", flex: 2 },
+ {
+ field: "PyTorch",
+ headerName: "PyTorch",
+ cellRenderer: params => params.value ? "✅" : "âŒ",
+ },
+ {
+ field: "TensorFlow",
+ headerName: "TensorFlow",
+ cellRenderer: params => params.value ? "✅" : "âŒ",
+ },
+ ],
+ defaultColDef: {
+ flex: 1,
+ filter: true,
+ // floatingFilter: true,
+ },
+ pagination: true,
+ paginationAutoPageSize: true
+ };
+ // Create Grid: Create new grid within the #myGrid div, using the Grid Options object
+ gridApi = agGrid.createGrid(document.querySelector("#grid"), gridOptions);
+</script>
\ No newline at end of file
diff --git a/docs/source/index.rst b/docs/source/index.rst
index b0f632e1f58ee97553b0014d030362264f7f736d..6ab1367719dbb62b03f7168627e9d2a80b3990da 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -114,3 +114,9 @@ Quick Links
:click-parent:
Contributor's Guide
+
+Models Available
+^^^^^^^^^^^^^^^^
+
+.. raw:: html
+ :file: _static/models/models.html
\ No newline at end of file