Graph Attention Interaction Aggregation Network for Click-Through Rate Prediction
Click-through rate prediction is a critical task for computational advertising and recommendation systems, where the key challenge is to model feature interactions between different feature domains. At present, the main click-through rate prediction models model feature interactions in an implicit w...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/24/9691 |
| _version_ | 1797455370151526400 |
|---|---|
| author | Wei Zhang Zhaobin Kang Lingling Song Kaiyuan Qu |
| author_facet | Wei Zhang Zhaobin Kang Lingling Song Kaiyuan Qu |
| author_sort | Wei Zhang |
| collection | DOAJ |
| description | Click-through rate prediction is a critical task for computational advertising and recommendation systems, where the key challenge is to model feature interactions between different feature domains. At present, the main click-through rate prediction models model feature interactions in an implicit way, which leads to poor interpretation of the model, and the interaction between each pair of features may introduce noise into the model, thus limiting the predictive ability of the model. In response to the above problems, this paper proposes a click-through rate prediction model (GAIAN) based on the graph attention interactive aggregation network, which explicitly obtains cross features on the graph structure. Our specific method is to design a feature interactive selection mechanism to select cross features that are beneficial to model prediction, reducing model noise and reducing the risk of model overfitting. On this basis, the bilinear interaction function is integrated into the aggregation strategy of the graph neural network, and the fine-grained intersection features are extracted in a flexible and explicit way, which makes graph neural networks more suitable for modeling feature interactions and enhances the interpretability of the model. Compared with several other state-of-the-art models on the Criteo and Avazu datasets, the experimental results show the superiority of the model. |
| first_indexed | 2024-03-09T15:52:28Z |
| format | Article |
| id | doaj.art-4c6f778249ac4eb1b7bceb430eb36c3b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T15:52:28Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4c6f778249ac4eb1b7bceb430eb36c3b2023-11-24T17:53:45ZengMDPI AGSensors1424-82202022-12-012224969110.3390/s22249691Graph Attention Interaction Aggregation Network for Click-Through Rate PredictionWei Zhang0Zhaobin Kang1Lingling Song2Kaiyuan Qu3Department of Artificial Intelligence Education, Central China Normal University, Wuhan 430079, ChinaDepartment of Artificial Intelligence Education, Central China Normal University, Wuhan 430079, ChinaDepartment of Artificial Intelligence Education, Central China Normal University, Wuhan 430079, ChinaDepartment of Artificial Intelligence Education, Central China Normal University, Wuhan 430079, ChinaClick-through rate prediction is a critical task for computational advertising and recommendation systems, where the key challenge is to model feature interactions between different feature domains. At present, the main click-through rate prediction models model feature interactions in an implicit way, which leads to poor interpretation of the model, and the interaction between each pair of features may introduce noise into the model, thus limiting the predictive ability of the model. In response to the above problems, this paper proposes a click-through rate prediction model (GAIAN) based on the graph attention interactive aggregation network, which explicitly obtains cross features on the graph structure. Our specific method is to design a feature interactive selection mechanism to select cross features that are beneficial to model prediction, reducing model noise and reducing the risk of model overfitting. On this basis, the bilinear interaction function is integrated into the aggregation strategy of the graph neural network, and the fine-grained intersection features are extracted in a flexible and explicit way, which makes graph neural networks more suitable for modeling feature interactions and enhances the interpretability of the model. Compared with several other state-of-the-art models on the Criteo and Avazu datasets, the experimental results show the superiority of the model.https://www.mdpi.com/1424-8220/22/24/9691click-through rate predictionrecommender systemsfeature interactiongraph neural networkattention mechanism |
| spellingShingle | Wei Zhang Zhaobin Kang Lingling Song Kaiyuan Qu Graph Attention Interaction Aggregation Network for Click-Through Rate Prediction Sensors click-through rate prediction recommender systems feature interaction graph neural network attention mechanism |
| title | Graph Attention Interaction Aggregation Network for Click-Through Rate Prediction |
| title_full | Graph Attention Interaction Aggregation Network for Click-Through Rate Prediction |
| title_fullStr | Graph Attention Interaction Aggregation Network for Click-Through Rate Prediction |
| title_full_unstemmed | Graph Attention Interaction Aggregation Network for Click-Through Rate Prediction |
| title_short | Graph Attention Interaction Aggregation Network for Click-Through Rate Prediction |
| title_sort | graph attention interaction aggregation network for click through rate prediction |
| topic | click-through rate prediction recommender systems feature interaction graph neural network attention mechanism |
| url | https://www.mdpi.com/1424-8220/22/24/9691 |
| work_keys_str_mv | AT weizhang graphattentioninteractionaggregationnetworkforclickthroughrateprediction AT zhaobinkang graphattentioninteractionaggregationnetworkforclickthroughrateprediction AT linglingsong graphattentioninteractionaggregationnetworkforclickthroughrateprediction AT kaiyuanqu graphattentioninteractionaggregationnetworkforclickthroughrateprediction |