Skip to content

Commit

Permalink
Add EulerNet model from SIGIR23 (#107)
Browse files Browse the repository at this point in the history
  • Loading branch information
@Ethan-TZ
Ethan-TZ committed Aug 12, 2024
1 parent 789bb88 commit 45c36db
Show file tree
Hide file tree
Showing 9 changed files with 316 additions and 15 deletions.
31 changes: 16 additions & 15 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -71,25 +71,26 @@ Click-through rate (CTR) prediction is a critical task for various industrial ap
| 35 | KDD'21 | [AOANet](./model_zoo/AOANet) | [Architecture and Operation Adaptive Network for Online Recommendations](https://dl.acm.org/doi/10.1145/3447548.3467133) :triangular_flag_on_post:**Didi Chuxing** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/AOANet) | `torch` |
| 36 | AAAI'23 | [FinalMLP](./model_zoo/FinalMLP) | [FinalMLP: An Enhanced Two-Stream MLP Model for CTR Prediction](https://arxiv.org/abs/2304.00902) :triangular_flag_on_post:**Huawei** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/FinalMLP) | `torch` |
| 37 | SIGIR'23 | [FinalNet](./model_zoo/FinalNet) | [FINAL: Factorized Interaction Layer for CTR Prediction](https://dl.acm.org/doi/10.1145/3539618.3591988) :triangular_flag_on_post:**Huawei** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/FinalNet) | `torch` |
| 38 | CIKM'23 | [GDCN](./model_zoo/GDCN) | [Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction](https://dl.acm.org/doi/pdf/10.1145/3583780.3615089) :triangular_flag_on_post:**Microsoft** | | `torch` |
| 39 | Arxiv'24 | [DCNv3](./model_zoo/DCNv3) | [DCNv3: Towards Next Generation Deep Cross Network for Click-Through Rate Prediction](https://arxiv.org/abs/2407.13349) :triangular_flag_on_post:**AHU, Huawei** | [:arrow_upper_right:](https://github.com/salmon1802/DCNv3/tree/master/checkpoints) | `torch` |
| 38 | SIGIR'23 | [EulerNet](./model_zoo/EulerNet) | [EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction](https://dl.acm.org/doi/10.1145/3539618.3591681) :triangular_flag_on_post:**Huawei** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/EulerNet) | `torch` |
| 39 | CIKM'23 | [GDCN](./model_zoo/GDCN) | [Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction](https://dl.acm.org/doi/pdf/10.1145/3583780.3615089) :triangular_flag_on_post:**Microsoft** | | `torch` |
| 40 | Arxiv'24 | [DCNv3](./model_zoo/DCNv3) | [DCNv3: Towards Next Generation Deep Cross Network for Click-Through Rate Prediction](https://arxiv.org/abs/2407.13349) :triangular_flag_on_post:**AHU, Huawei** | [:arrow_upper_right:](https://github.com/salmon1802/DCNv3/tree/master/checkpoints) | `torch` |
|<tr><th colspan=6 align="center">:open_file_folder: **Behavior Sequence Modeling**</th></tr>|
| 40 | KDD'18 | [DIN](./model_zoo/DIN) | [Deep Interest Network for Click-Through Rate Prediction](https://www.kdd.org/kdd2018/accepted-papers/view/deep-interest-network-for-click-through-rate-prediction) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/DIN) | `torch` |
| 41 | AAAI'19 | [DIEN](./model_zoo/DIEN) | [Deep Interest Evolution Network for Click-Through Rate Prediction](https://arxiv.org/abs/1809.03672) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/DIEN) | `torch` |
| 42 | DLP-KDD'19 | [BST](./model_zoo/BST) | [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba](https://arxiv.org/abs/1905.06874) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/BST) | `torch` |
| 43 | CIKM'20 | [DMIN](./model_zoo/DMIN) | [Deep Multi-Interest Network for Click-through Rate Prediction](https://dl.acm.org/doi/10.1145/3340531.3412092) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/DMIN) | `torch` |
| 44 | AAAI'20 | [DMR](./model_zoo/DMR) | [Deep Match to Rank Model for Personalized Click-Through Rate Prediction](https://ojs.aaai.org/index.php/AAAI/article/view/5346) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/DMR) | `torch` |
| 45 | Arxiv'21 | [ETA](./model_zoo/ETA) | [End-to-End User Behavior Retrieval in Click-Through RatePrediction Model](https://arxiv.org/abs/2108.04468) :triangular_flag_on_post:**Alibaba** | | `torch` |
| 46 | CIKM'22 | [SDIM](./model_zoo/SDIM) | [Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction](https://arxiv.org/abs/2205.10249) :triangular_flag_on_post:**Meituan** | | `torch` |
| 41 | KDD'18 | [DIN](./model_zoo/DIN) | [Deep Interest Network for Click-Through Rate Prediction](https://www.kdd.org/kdd2018/accepted-papers/view/deep-interest-network-for-click-through-rate-prediction) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/DIN) | `torch` |
| 42 | AAAI'19 | [DIEN](./model_zoo/DIEN) | [Deep Interest Evolution Network for Click-Through Rate Prediction](https://arxiv.org/abs/1809.03672) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/DIEN) | `torch` |
| 43 | DLP-KDD'19 | [BST](./model_zoo/BST) | [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba](https://arxiv.org/abs/1905.06874) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/BST) | `torch` |
| 44 | CIKM'20 | [DMIN](./model_zoo/DMIN) | [Deep Multi-Interest Network for Click-through Rate Prediction](https://dl.acm.org/doi/10.1145/3340531.3412092) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/DMIN) | `torch` |
| 45 | AAAI'20 | [DMR](./model_zoo/DMR) | [Deep Match to Rank Model for Personalized Click-Through Rate Prediction](https://ojs.aaai.org/index.php/AAAI/article/view/5346) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/DMR) | `torch` |
| 46 | Arxiv'21 | [ETA](./model_zoo/ETA) | [End-to-End User Behavior Retrieval in Click-Through RatePrediction Model](https://arxiv.org/abs/2108.04468) :triangular_flag_on_post:**Alibaba** | | `torch` |
| 47 | CIKM'22 | [SDIM](./model_zoo/SDIM) | [Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction](https://arxiv.org/abs/2205.10249) :triangular_flag_on_post:**Meituan** | | `torch` |
|<tr><th colspan=6 align="center">:open_file_folder: **Dynamic Weight Network**</th></tr>|
| 47 | NeurIPS'22 | [APG](./model_zoo/APG) | [APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction](https://arxiv.org/abs/2203.16218) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/APG) | `torch` |
| 48 | KDD'23 | [PPNet](./model_zoo/PEPNet) | [PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information](https://arxiv.org/abs/2302.01115) :triangular_flag_on_post:**KuaiShou** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/PPNet) | `torch` |
| 48 | NeurIPS'22 | [APG](./model_zoo/APG) | [APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction](https://arxiv.org/abs/2203.16218) :triangular_flag_on_post:**Alibaba** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/APG) | `torch` |
| 49 | KDD'23 | [PPNet](./model_zoo/PEPNet) | [PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information](https://arxiv.org/abs/2302.01115) :triangular_flag_on_post:**KuaiShou** | [:arrow_upper_right:](https://github.com/reczoo/BARS/tree/main/ranking/ctr/PPNet) | `torch` |
|<tr><th colspan=6 align="center">:open_file_folder: **Multi-Task Modeling**</th></tr>|
| 49 | MachineLearn'97 | [SharedBottom](./model_zoo/multitask/SharedBottom) | [Multitask Learning](https://link.springer.com/article/10.1023/A:1007379606734) | | `torch` |
| 50 | KDD'18 | [MMoE](./model_zoo/multitask/MMOE) | [Modeling Task Relationships in Multi-task Learning with Multi-Gate Mixture-of-Experts](https://dl.acm.org/doi/pdf/10.1145/3219819.3220007) :triangular_flag_on_post:**Google** | | `torch` |
| 51 | KDD'18 | [PLE](./model_zoo/multitask/PLE) | [Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations](https://dl.acm.org/doi/10.1145/3383313.3412236) :triangular_flag_on_post:**Tencent** | | `torch` |
| 50 | MachineLearn'97 | [SharedBottom](./model_zoo/multitask/SharedBottom) | [Multitask Learning](https://link.springer.com/article/10.1023/A:1007379606734) | | `torch` |
| 51 | KDD'18 | [MMoE](./model_zoo/multitask/MMOE) | [Modeling Task Relationships in Multi-task Learning with Multi-Gate Mixture-of-Experts](https://dl.acm.org/doi/pdf/10.1145/3219819.3220007) :triangular_flag_on_post:**Google** | | `torch` |
| 52 | KDD'18 | [PLE](./model_zoo/multitask/PLE) | [Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations](https://dl.acm.org/doi/10.1145/3383313.3412236) :triangular_flag_on_post:**Tencent** | | `torch` |
|<tr><th colspan=6 align="center">:open_file_folder: **Multi-Domain Modeling**</th></tr>|
| 52 | KDD'23 | PEPNet | [PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information](https://arxiv.org/abs/2302.01115) :triangular_flag_on_post:**KuaiShou** | | `torch` |
| 53 | KDD'23 | PEPNet | [PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information](https://arxiv.org/abs/2302.01115) :triangular_flag_on_post:**KuaiShou** | | `torch` |

## Benchmarking

Expand Down
7 changes: 7 additions & 0 deletions model_zoo/EulerNet/config/dataset_config.yaml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
### Tiny data for tests only
tiny_npz:
data_root: ../../data/
data_format: npz
train_data: ../../data/tiny_npz/train.npz
valid_data: ../../data/tiny_npz/valid.npz
test_data: ../../data/tiny_npz/test.npz
57 changes: 57 additions & 0 deletions model_zoo/EulerNet/config/model_config.yaml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,57 @@
Base:
model_root: './checkpoints/'
num_workers: 3
verbose: 1
early_stop_patience: 2
pickle_feature_encoder: True
save_best_only: True
eval_steps: null
debug_mode: False
group_id: null
use_features: null
feature_specs: null
feature_config: null

EulerNet_test: # This is a config template
model: EulerNet
dataset_id: tiny_npz
loss: 'binary_crossentropy'
metrics: ['logloss', 'AUC']
task: binary_classification
optimizer: adam
shape: [52]
net_ex_dropout: 0.1
net_im_dropout: 0.1
layer_norm: true
learning_rate: 1.0e-3
embedding_regularizer: 0
net_regularizer: 0
batch_size: 10000
embedding_dim: 10
epochs: 100
shuffle: True
seed: 2021
monitor: {'AUC': 1, 'logloss': -1}
monitor_mode: 'max'

EulerNet_test: # This is a config template
model: EulerNet
dataset_id: TBD
loss: 'binary_crossentropy'
metrics: ['logloss', 'AUC']
task: binary_classification
optimizer: adam
shape: [20]
net_ex_dropout: 0.0
net_im_dropout: 0.0
layer_norm: true
learning_rate: 1.0e-3
embedding_regularizer: 0
net_regularizer: 0
batch_size: 10000
embedding_dim: 10
epochs: 100
shuffle: True
seed: 2021
monitor: {'AUC': 1, 'logloss': -1}
monitor_mode: 'max'
3 changes: 3 additions & 0 deletions model_zoo/EulerNet/fuxictr_version.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
# pip install -U fuxictr
import fuxictr
assert fuxictr.__version__ >= "2.2.0"
16 changes: 16 additions & 0 deletions model_zoo/EulerNet/readme.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
## Tuning
The detailed tuning config files are provided in this repo: https://github.com/Ethan-TZ/EulerNet/tree/main/%23Code4FuxiCTR%23.

## Cite

If you find EulerNet useful for your research or development, please cite the following papers: [EulerNet](https://dl.acm.org/doi/10.1145/3539618.3591681).

```bibtex
@inproceedings{tian2023eulernet,
title = {EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction},
author = {Tian, Zhen and Bai, Ting and Zhao, Wayne Xin and Wen, Ji-Rong and Cao, Zhao},
booktitle = {Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval},
pages = {1376–1385},
year = {2023},
}
```
Loading

0 comments on commit 45c36db

Please sign in to comment.