Merge pull request #1901 from TayTroye/docs

zhengbw0324 · web-flow · commit 7a574e40397c · 2023-11-02T11:05:07.000+08:00
FIX: update docs
diff --git a/asset/dataset_list.json b/asset/dataset_list.json
diff --git a/asset/model_list.json b/asset/model_list.json
@@ -1987,33 +1987,6 @@
         "repository": "RecBole",
         "repo_link": "https://github.com/RUCAIBox/RecBole"
     },
-    {
-        "category": "Sequential Recommendation",
-        "cate_link": "/docs/user_guide/model_intro.html#sequential-recommendation",
-        "year": "2018",
-        "pub": "ICDM'18",
-        "model": "SASRec",
-        "model_link": "/docs/user_guide/model/sequential/sasrec.html",
-        "paper": "Self-Attentive Sequential Recommendation",
-        "paper_link": "https://doi.org/10.1109/ICDM.2018.00035",
-        "authors": "Wang-Cheng Kang and Julian McAuley",
-        "ref_code": "https://github.com/kang205/SASRec",
-        "repository": "RecBole",
-        "repo_link": "https://github.com/RUCAIBox/RecBole"
-    },
-    {
-        "category": "Knowledge-aware Recommendation",
-        "year": "2018",
-        "pub": "MDPI'18",
-        "model": "CFKG",
-        "model_link": "/docs/user_guide/model/knowledge/cfkg.html",
-        "paper": "Learning heterogeneous knowledge base embeddings for explainable recommendation",
-        "paper_link": "https://doi.org/10.3390/a11090137",
-        "authors": "Qingyao Ai, Vahid Azizi, Xu Chen, Yongfeng Zhang",
-        "ref_code": "",
-        "repository": "RecBole",
-        "repo_link": "https://github.com/RUCAIBox/RecBole"
-    },
     {
         "category": "Knowledge-aware Recommendation",
         "year": "2018",
@@ -2143,6 +2116,62 @@
         "ref_code": "",
         "repository": "RecBole",
         "repo_link": "https://github.com/RUCAIBox/RecBole"
+    },
+    {
+        "category": "Context-aware Recommendation",
+        "cate_link": "/docs/user_guide/model_intro.html#context-aware-recommendation",
+        "year": "2023",
+        "pub": "SIGIR'23",
+        "model": "EulerNet",
+        "model_link": "/docs/user_guide/model/context/eulernet.html",
+        "paper": "EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction",
+        "paper_link": "https://dl.acm.org/doi/10.1145/3539618.3591681",
+        "authors": "Zhen Tian, Ting Bai, Wayne Xin Zhao, Ji-Rong Wen, Zhao Cao",
+        "ref_code": "https://github.com/chenyuwuxin/EulerNet",
+        "repository": "RecBole",
+        "repo_link": "https://github.com/RUCAIBox/RecBole"
+      },
+      {
+        "category": "Sequential Recommendation",
+        "cate_link":  "/docs/user_guide/model_intro.html#sequential-recommendation",
+        "year": "2023",
+        "pub": "SIGIR'23",
+        "model": "FEARec",
+        "model_link": "/docs/user_guide/model/sequential/fearec.html",
+        "paper": "FEARec: Frequency Enhanced Hybrid Attention Network for Sequential Recommendation",
+        "paper_link": "https://dl.acm.org/doi/10.1145/3539618.3591689",
+        "authors": "Xinyu Du, Huanhuan Yuan, Pengpeng Zhao, Jianfeng Qu, Fuzhen Zhuang, Guanfeng Liu, Victor S. Sheng",
+        "ref_code": "https://github.com/sudaada/FEARec",
+        "repository": "RecBole",
+        "repo_link": "https://github.com/RUCAIBox/RecBole"
+      },
+      {
+        "category": "General Recommendation",
+        "cate_link": "/docs/user_guide/model_intro.html#general-recommendation",
+        "year": "2023",
+        "pub": "SIGIR'23",
+        "model": "DiffRec",
+        "model_link": "/docs/user_guide/model/general/diffrec.html",
+        "paper": "Diffusion Recommender Model",
+        "paper_link": "https://dl.acm.org/doi/10.1145/3539618.3591663",
+        "authors": "Wenjie Wang, Yiyan Xu, Fuli Feng, Xinyu Lin, Xiangnan He, Tat-Seng Chua",
+        "ref_code": "https://github.com/YiyanXu/DiffRec",
+        "repository": "RecBole",
+        "repo_link": "https://github.com/RUCAIBox/RecBole"
+    },
+    {
+        "category": "General Recommendation",
+        "cate_link": "/docs/user_guide/model_intro.html#general-recommendation",
+        "year": "2023",
+        "pub": "SIGIR'23",
+        "model": "LDiffRec",
+        "model_link": "/docs/user_guide/model/general/ldiffrec.html",
+        "paper": "Diffusion Recommender Model",
+        "paper_link": "https://dl.acm.org/doi/10.1145/3539618.3591663",
+        "authors": "Wenjie Wang, Yiyan Xu, Fuli Feng, Xinyu Lin, Xiangnan He, Tat-Seng Chua",
+        "ref_code": "https://github.com/YiyanXu/DiffRec",
+        "repository": "RecBole",
+        "repo_link": "https://github.com/RUCAIBox/RecBole"
     }
   ]
 }
diff --git a/docs/source/asset/eulernet.png b/docs/source/asset/eulernet.png
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -20,11 +20,11 @@
 # -- Project information -----------------------------------------------------
 
 project = "RecBole"
-copyright = "2020-2022, RecBole Contributors"
+copyright = "2020-2023, RecBole Contributors"
 author = "AIBox RecBole group"
 
 # The full version, including alpha/beta/rc tags
-release = "1.1.1"
+release = "1.2.0"
 
 
 # -- General configuration ---------------------------------------------------
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -1,24 +1,24 @@
 .. RecBole documentation master file.
-.. title:: RecBole v1.1.1
+.. title:: RecBole v1.2.0
 .. image:: asset/logo.png
 
 =========================================================
 
-`HomePage <https://recbole.io/>`_ | `Docs <https://recbole.io/docs/>`_ | `GitHub <https://github.com/RUCAIBox/RecBole>`_ | `Datasets <https://github.com/RUCAIBox/RecDatasets>`_ | `v0.1.2 </docs/v0.1.2/>`_ | `v0.2.0 </docs/v0.2.0/>`_ | `v1.0.0 </docs/v1.0.0/>`_ | `v1.0.1 </docs/v1.0.1/>`_
+`HomePage <https://recbole.io/>`_ | `Docs <https://recbole.io/docs/>`_ | `GitHub <https://github.com/RUCAIBox/RecBole>`_ | `Datasets <https://github.com/RUCAIBox/RecDatasets>`_ | `v0.1.2 </docs/v0.1.2/>`_ | `v0.2.0 </docs/v0.2.0/>`_ | `v1.0.0 </docs/v1.0.0/>`_ | `v1.0.1 </docs/v1.0.1/>`_ | `v1.2.0 </docs/v1.2.0/>`_
 
 Introduction
 -------------------------
 RecBole is a unified, comprehensive and efficient framework developed based on PyTorch.
 It aims to help the researchers to reproduce and develop recommendation models.
 
-In the lastest release, our library includes 90 recommendation algorithms `[Model List]`_, covering four major categories:
+In the lastest release, our library includes 91 recommendation algorithms `[Model List]`_, covering four major categories:
 
 - General Recommendation
 - Sequential Recommendation
 - Context-aware Recommendation
 - Knowledge-based Recommendation
 
-We design a unified and flexible data file format, and provide the support for 41 benchmark recommendation datasets `[Collected Datasets]`_. A user can apply the provided script to process the original data copy, or simply download the processed datasets by our team.
+We design a unified and flexible data file format, and provide the support for 43 benchmark recommendation datasets `[Collected Datasets]`_. A user can apply the provided script to process the original data copy, or simply download the processed datasets by our team.
 
 .. image:: asset/framework.png
     :width: 600
@@ -29,7 +29,7 @@ Features:
 - General and extensible data structure
     We deign general and extensible data structures to unify the formatting and usage of various recommendation datasets.
 - Comprehensive benchmark models and datasets
-    We implement 86 commonly used recommendation algorithms, and provide the formatted copies of 41 recommendation datasets.
+    We implement 91 commonly used recommendation algorithms, and provide the formatted copies of 43 recommendation datasets.
 - Efficient GPU-accelerated execution
     We design many tailored strategies in the GPU environment to enhance the efficiency of our library.
 - Extensive and standard evaluation protocols
diff --git a/docs/source/recbole/recbole.model.context_aware_recommender.eulernet.rst b/docs/source/recbole/recbole.model.context_aware_recommender.eulernet.rst
@@ -0,0 +1,4 @@
+.. automodule:: recbole.model.context_aware_recommender.eulernet
+   :members:
+   :undoc-members:
+   :show-inheritance:
diff --git a/docs/source/recbole/recbole.model.context_aware_recommender.rst b/docs/source/recbole/recbole.model.context_aware_recommender.rst
@@ -7,12 +7,16 @@ recbole.model.context\_aware\_recommender
    recbole.model.context_aware_recommender.afm
    recbole.model.context_aware_recommender.autoint
    recbole.model.context_aware_recommender.dcn
+   recbole.model.context_aware_recommender.dcnv2
    recbole.model.context_aware_recommender.deepfm
    recbole.model.context_aware_recommender.dssm
+   recbole.model.context_aware_recommender.eulernet
    recbole.model.context_aware_recommender.ffm
+   recbole.model.context_aware_recommender.fignn
    recbole.model.context_aware_recommender.fm
    recbole.model.context_aware_recommender.fnn
    recbole.model.context_aware_recommender.fwfm
+   recbole.model.context_aware_recommender.kd_dagfm
    recbole.model.context_aware_recommender.lr
    recbole.model.context_aware_recommender.nfm
    recbole.model.context_aware_recommender.pnn
diff --git a/docs/source/recbole/recbole.model.general_recommender.diffrec.rst b/docs/source/recbole/recbole.model.general_recommender.diffrec.rst
@@ -0,0 +1,4 @@
+.. automodule:: recbole.model.general_recommender.diffrec
+   :members:
+   :undoc-members:
+   :show-inheritance:
diff --git a/docs/source/recbole/recbole.model.general_recommender.ldiffrec.rst b/docs/source/recbole/recbole.model.general_recommender.ldiffrec.rst
@@ -0,0 +1,4 @@
+.. automodule:: recbole.model.general_recommender.ldiffrec
+   :members:
+   :undoc-members:
+   :show-inheritance:
diff --git a/docs/source/recbole/recbole.model.general_recommender.random.rst b/docs/source/recbole/recbole.model.general_recommender.random.rst
@@ -0,0 +1,4 @@
+.. automodule:: recbole.model.general_recommender.random
+   :members:
+   :undoc-members:
+   :show-inheritance:
diff --git a/docs/source/recbole/recbole.model.general_recommender.rst b/docs/source/recbole/recbole.model.general_recommender.rst
@@ -4,24 +4,35 @@ recbole.model.general\_recommender
 .. toctree::
    :maxdepth: 4
 
+   recbole.model.general_recommender.admmslim
    recbole.model.general_recommender.bpr
    recbole.model.general_recommender.cdae
    recbole.model.general_recommender.convncf
    recbole.model.general_recommender.dgcf
    recbole.model.general_recommender.dmf
+   recbole.model.general_recommender.diffrec
+   recbole.model.general_recommender.ease
+   recbole.model.general_recommender.enmf
    recbole.model.general_recommender.fism
    recbole.model.general_recommender.gcmc
    recbole.model.general_recommender.itemknn
+   recbole.model.general_recommender.ldiffrec
    recbole.model.general_recommender.lightgcn
    recbole.model.general_recommender.line
    recbole.model.general_recommender.macridvae
    recbole.model.general_recommender.multidae
    recbole.model.general_recommender.multivae
    recbole.model.general_recommender.nais
+   recbole.model.general_recommender.nceplrec
+   recbole.model.general_recommender.ncl
    recbole.model.general_recommender.neumf
    recbole.model.general_recommender.ngcf
+   recbole.model.general_recommender.nncf
    recbole.model.general_recommender.pop
+   recbole.model.general_recommender.ract
+   recbole.model.general_recommender.random
+   recbole.model.general_recommender.recvae
    recbole.model.general_recommender.sgl
    recbole.model.general_recommender.simplex
+   recbole.model.general_recommender.slimelastic
    recbole.model.general_recommender.spectralcf
-   recbole.model.general_recommender.ncl
diff --git a/docs/source/recbole/recbole.model.knowledge_aware_recommender.rst b/docs/source/recbole/recbole.model.knowledge_aware_recommender.rst
@@ -8,7 +8,9 @@ recbole.model.knowledge\_aware\_recommender
    recbole.model.knowledge_aware_recommender.cke
    recbole.model.knowledge_aware_recommender.kgat
    recbole.model.knowledge_aware_recommender.kgcn
+   recbole.model.knowledge_aware_recommender.kgin
    recbole.model.knowledge_aware_recommender.kgnnls
    recbole.model.knowledge_aware_recommender.ktup
+   recbole.model.knowledge_aware_recommender.mcclk
    recbole.model.knowledge_aware_recommender.mkr
    recbole.model.knowledge_aware_recommender.ripplenet
diff --git a/docs/source/recbole/recbole.model.sequential_recommender.fearec.rst b/docs/source/recbole/recbole.model.sequential_recommender.fearec.rst
@@ -0,0 +1,4 @@
+.. automodule:: recbole.model.sequential_recommender.fearec
+   :members:
+   :undoc-members:
+   :show-inheritance:
diff --git a/docs/source/recbole/recbole.model.sequential_recommender.rst b/docs/source/recbole/recbole.model.sequential_recommender.rst
@@ -29,3 +29,4 @@ recbole.model.sequential\_recommender
    recbole.model.sequential_recommender.srgnn
    recbole.model.sequential_recommender.stamp
    recbole.model.sequential_recommender.transrec
+   recbole.model.sequential_recommender.fearec
diff --git a/docs/source/user_guide/data_intro.rst b/docs/source/user_guide/data_intro.rst
@@ -1,7 +1,7 @@
 Data Module Introduction
 =========================
 
-RecBole not only implements lots of popular recommender models, but also collects and releases 41 commonly-used publiced datasets.
+RecBole not only implements lots of popular recommender models, but also collects and releases 43 commonly-used publiced datasets.
 You can freely download these datasets following our docs :doc:`data/dataset_download`.
 
 For extensibility and reusability, Recbole has a flexible and extensible data module.  
diff --git a/docs/source/user_guide/model/context/eulernet.rst b/docs/source/user_guide/model/context/eulernet.rst
@@ -0,0 +1,78 @@
+EulerNet
+===========
+
+Introduction
+---------------------
+
+`[paper] <https://dl.acm.org/doi/10.1145/3539618.3591681>`_
+
+**Title:** EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction
+
+**Authors:** Zhen Tian, Ting Bai, Wayne Xin Zhao, Ji-Rong Wen, Zhao Cao
+
+**Abstract:**  Learning effective high-order feature interactions is very crucial in the CTR prediction task. However, it is very time-consuming to calculate high-order feature interactions with massive features in online e-commerce platforms. Most existing methods manually design a maximal order and further filter out the useless interactions from them. Although they reduce the high computational costs caused by the exponential growth of high-order feature combinations, they still suffer from the degradation of model capability due to the suboptimal learning of the restricted feature orders. The solution to maintain the model capability and meanwhile keep it efficient is a technical challenge, which has not been adequately addressed. To address this issue, we propose an adaptive feature interaction learning model, named as EulerNet, in which the feature interactions are learned in a complex vector space by conducting space mapping according to Euler's formula. EulerNet converts the exponential powers of feature interactions into simple linear combinations of the modulus and phase of the complex features, making it possible to adaptively learn the high-order feature interactions in an efficient way. Furthermore, EulerNet incorporates the implicit and explicit feature interactions into a unified architecture, which achieves the mutual enhancement and largely boosts the model capabilities. Such a network can be fully learned from data, with no need of pre-designed form or order for feature interactions. Extensive experiments conducted on three public datasets have demonstrated the effectiveness and efficiency of our approach. 
+
+.. image:: ../../../asset/eulernet.png  
+    :width: 500
+    :align: center
+
+Quick Start with RecBole
+-------------------------
+
+**Model Hyper-Parameters:**
+
+- ``embedding_size (int)`` : The embedding size of features. Defaults to ``16``.
+- ``order_list (list)`` : The order vectors of EulerNet.Defaults to ``[30]``.
+- ``drop_ex (float)`` : The dropout rate for the modulus and phase. Defaults to ``0.3``.
+- ``drop_im (float)`` : The dropout rate for the real and imaginary part. Defaults to ``0.3``.
+- ``apply_norm (bool)`` : Whether perform the layer norm. Defaults to ``False``.
+- ``reg_weight (float)`` : The L2 regularization weight. Defaults to ``1e-5``.
+
+**A Running Example:**
+
+Write the following code to a python file, such as `run.py`
+
+.. code:: python
+
+   from recbole.quick_start import run_recbole
+
+   run_recbole(model='EulerNet', dataset='ml-100k')
+
+And then:
+
+.. code:: bash
+
+   python run.py
+
+Tuning Hyper Parameters
+-------------------------
+
+If you want to use ``HyperTuning`` to tune hyper parameters of this model, you can copy the following settings and name it as ``hyper.test``.
+
+.. code:: bash
+
+    learning_rate choice [1e-3,1e-4,1e-5]
+    reg_weight choice [1e-3,1e-5,1e-7]
+    order_list choice [7,10,20,30]
+    drop_ex choice [0.,0.1,0.2,0.3]
+    drop_im choice [0.,0.1,0.2,0.3]
+    apply_norm choice [True,False]
+
+Note that we just provide these hyper parameter ranges for reference only, and we can not guarantee that they are the optimal range of this model.
+
+Then, with the source code of RecBole (you can download it from GitHub), you can run the ``run_hyper.py`` to tuning:
+
+.. code:: bash
+
+	python run_hyper.py --model=[model_name] --dataset=[dataset_name] --config_files=[config_files_path] --params_file=hyper.test
+
+For more details about Parameter Tuning, refer to :doc:`../../../user_guide/usage/parameter_tuning`.
+
+
+If you want to change parameters, dataset or evaluation settings, take a look at
+
+- :doc:`../../../user_guide/config_settings`
+- :doc:`../../../user_guide/data_intro`
+- :doc:`../../../user_guide/train_eval_intro`
+- :doc:`../../../user_guide/usage`
+
diff --git a/docs/source/user_guide/model/sequential/fearec.rst b/docs/source/user_guide/model/sequential/fearec.rst
@@ -4,7 +4,7 @@ FEARec
 Introduction
 ---------------------
 
-`[paper] <https://arxiv.org/pdf/2304.09184.pdf>`_
+`[paper] <https://dl.acm.org/doi/10.1145/3539618.3591689>`_
 
 **Title:** FEARec: Frequency Enhanced Hybrid Attention Network for Sequential Recommendation
 
@@ -50,6 +50,10 @@ Write the following code to a python file, such as `run.py`
 
    from recbole.quick_start import run_recbole
 
+   parameter_dict = {
+      'train_neg_sample_args': None,
+   }
+
    run_recbole(model='FEARec', dataset='ml-100k')
 
 And then:
diff --git a/docs/source/user_guide/model_intro.rst b/docs/source/user_guide/model_intro.rst
@@ -1,6 +1,6 @@
 Model Introduction
 =====================
-We implement 90 recommendation models covering general recommendation, sequential recommendation,
+We implement 91 recommendation models covering general recommendation, sequential recommendation,
 context-aware recommendation and knowledge-based recommendation. A brief introduction to these models are as follows:
 
 
@@ -77,6 +77,7 @@ are also support for these models. And evaluation is always conducted in the way
    model/context/lightgbm
    model/context/kd_dagfm
    model/context/fignn
+   model/context/eulernet
 
 
 Sequential Recommendation
@@ -114,6 +115,7 @@ the sequential data. The models of session-based recommendation are also include
    model/sequential/lightsans
    model/sequential/sine
    model/sequential/core
+   model/sequential/fearec
 
 
 Knowledge-based Recommendation
diff --git a/recbole/model/general_recommender/__init__.py b/recbole/model/general_recommender/__init__.py
@@ -13,7 +13,6 @@
 from recbole.model.general_recommender.macridvae import MacridVAE
 from recbole.model.general_recommender.multidae import MultiDAE
 from recbole.model.general_recommender.multivae import MultiVAE
-from recbole.model.general_recommender.enmf import ENMF
 from recbole.model.general_recommender.nais import NAIS
 from recbole.model.general_recommender.ncl import NCL
 from recbole.model.general_recommender.neumf import NeuMF
diff --git a/recbole/model/sequential_recommender/fearec.py b/recbole/model/sequential_recommender/fearec.py
