From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912767675465728 |
|---|---|
| author | Yin, Mingjia Pan, Junwei Wang, Hao Wang, Ximei Zhang, Shangyu Jiang, Jie Lian, Defu Chen, Enhong |
| author_facet | Yin, Mingjia Pan, Junwei Wang, Hao Wang, Ximei Zhang, Shangyu Jiang, Jie Lian, Defu Chen, Enhong |
| contents | Click-Through Rate (CTR) prediction, a core task in recommendation systems, aims to estimate the probability of users clicking on items. Existing models predominantly follow a discriminative paradigm, which relies heavily on explicit interactions between raw ID embeddings. However, this paradigm inherently renders them susceptible to two critical issues: embedding dimensional collapse and information redundancy, stemming from the over-reliance on feature interactions \emph{over raw ID embeddings}. To address these limitations, we propose a novel \emph{Supervised Feature Generation (SFG)} framework, \emph{shifting the paradigm from discriminative ``feature interaction" to generative ``feature generation"}. Specifically, SFG comprises two key components: an \emph{Encoder} that constructs hidden embeddings for each feature, and a \emph{Decoder} tasked with regenerating the feature embeddings of all features from these hidden representations. Unlike existing generative approaches that adopt self-supervised losses, we introduce a supervised loss to utilize the supervised signal, \ie, click or not, in the CTR prediction task. This framework exhibits strong generalizability: it can be seamlessly integrated with most existing CTR models, reformulating them under the generative paradigm. Extensive experiments demonstrate that SFG consistently mitigates embedding collapse and reduces information redundancy, while yielding substantial performance gains across various datasets and base models. The code is available at https://github.com/USTC-StarTeam/GE4Rec. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14041 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models Yin, Mingjia Pan, Junwei Wang, Hao Wang, Ximei Zhang, Shangyu Jiang, Jie Lian, Defu Chen, Enhong Information Retrieval Click-Through Rate (CTR) prediction, a core task in recommendation systems, aims to estimate the probability of users clicking on items. Existing models predominantly follow a discriminative paradigm, which relies heavily on explicit interactions between raw ID embeddings. However, this paradigm inherently renders them susceptible to two critical issues: embedding dimensional collapse and information redundancy, stemming from the over-reliance on feature interactions \emph{over raw ID embeddings}. To address these limitations, we propose a novel \emph{Supervised Feature Generation (SFG)} framework, \emph{shifting the paradigm from discriminative ``feature interaction" to generative ``feature generation"}. Specifically, SFG comprises two key components: an \emph{Encoder} that constructs hidden embeddings for each feature, and a \emph{Decoder} tasked with regenerating the feature embeddings of all features from these hidden representations. Unlike existing generative approaches that adopt self-supervised losses, we introduce a supervised loss to utilize the supervised signal, \ie, click or not, in the CTR prediction task. This framework exhibits strong generalizability: it can be seamlessly integrated with most existing CTR models, reformulating them under the generative paradigm. Extensive experiments demonstrate that SFG consistently mitigates embedding collapse and reduces information redundancy, while yielding substantial performance gains across various datasets and base models. The code is available at https://github.com/USTC-StarTeam/GE4Rec. |
| title | From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2512.14041 |