Entity Representation Learning Through Onsite-Offsite Graph for Pinterest Ads
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911093544189952 |
|---|---|
| author | Jin, Jiayin Pan, Zhimeng Tang, Yang Feng, Jiarui Li, Kungang Xiang, Chongyuan Li, Jiacheng Su, Runze Ji, Siping Sun, Han Leng, Ling Deshikachar, Prathibha |
| author_facet | Jin, Jiayin Pan, Zhimeng Tang, Yang Feng, Jiarui Li, Kungang Xiang, Chongyuan Li, Jiacheng Su, Runze Ji, Siping Sun, Han Leng, Ling Deshikachar, Prathibha |
| contents | Graph Neural Networks (GNN) have been extensively applied to industry recommendation systems, as seen in models like GraphSage\cite{GraphSage}, TwHIM\cite{TwHIM}, LiGNN\cite{LiGNN} etc. In these works, graphs were constructed based on users' activities on the platforms, and various graph models were developed to effectively learn node embeddings. In addition to users' onsite activities, their offsite conversions are crucial for Ads models to capture their shopping interest. To better leverage offsite conversion data and explore the connection between onsite and offsite activities, we constructed a large-scale heterogeneous graph based on users' onsite ad interactions and opt-in offsite conversion activities. Furthermore, we introduced TransRA (TransR\cite{TransR} with Anchors), a novel Knowledge Graph Embedding (KGE) model, to more efficiently integrate graph embeddings into Ads ranking models. However, our Ads ranking models initially struggled to directly incorporate Knowledge Graph Embeddings (KGE), and only modest gains were observed during offline experiments. To address this challenge, we employed the Large ID Embedding Table technique and innovated an attention based KGE finetuning approach within the Ads ranking models. As a result, we observed a significant AUC lift in Click-Through Rate (CTR) and Conversion Rate (CVR) prediction models. Moreover, this framework has been deployed in Pinterest's Ads Engagement Model and contributed to $2.69\%$ CTR lift and $1.34\%$ CPC reduction. We believe the techniques presented in this paper can be leveraged by other large-scale industrial models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02609 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Entity Representation Learning Through Onsite-Offsite Graph for Pinterest Ads Jin, Jiayin Pan, Zhimeng Tang, Yang Feng, Jiarui Li, Kungang Xiang, Chongyuan Li, Jiacheng Su, Runze Ji, Siping Sun, Han Leng, Ling Deshikachar, Prathibha Machine Learning Artificial Intelligence Software Engineering Graph Neural Networks (GNN) have been extensively applied to industry recommendation systems, as seen in models like GraphSage\cite{GraphSage}, TwHIM\cite{TwHIM}, LiGNN\cite{LiGNN} etc. In these works, graphs were constructed based on users' activities on the platforms, and various graph models were developed to effectively learn node embeddings. In addition to users' onsite activities, their offsite conversions are crucial for Ads models to capture their shopping interest. To better leverage offsite conversion data and explore the connection between onsite and offsite activities, we constructed a large-scale heterogeneous graph based on users' onsite ad interactions and opt-in offsite conversion activities. Furthermore, we introduced TransRA (TransR\cite{TransR} with Anchors), a novel Knowledge Graph Embedding (KGE) model, to more efficiently integrate graph embeddings into Ads ranking models. However, our Ads ranking models initially struggled to directly incorporate Knowledge Graph Embeddings (KGE), and only modest gains were observed during offline experiments. To address this challenge, we employed the Large ID Embedding Table technique and innovated an attention based KGE finetuning approach within the Ads ranking models. As a result, we observed a significant AUC lift in Click-Through Rate (CTR) and Conversion Rate (CVR) prediction models. Moreover, this framework has been deployed in Pinterest's Ads Engagement Model and contributed to $2.69\%$ CTR lift and $1.34\%$ CPC reduction. We believe the techniques presented in this paper can be leveraged by other large-scale industrial models. |
| title | Entity Representation Learning Through Onsite-Offsite Graph for Pinterest Ads |
| topic | Machine Learning Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2508.02609 |