An Efficient Embedding Based Ad Retrieval With Gpu-powered Feature Interaction

Abstract

In large-scale advertising recommendation systems, retrieval serves as a critical component, aiming to efficiently select a subset of candidate ads relevant to user behaviors from a massive ad inventory for subsequent ranking and recommendation. The Embedding-Based Retrieval (EBR) methods modeled by the dual-tower network are widely used in the industry to maintain both retrieval efficiency and accuracy. However, the dual-tower model has significant limitations: the embeddings of users and ads interact only at the final inner product computation, resulting in insufficient feature interaction capabilities. Although DNN-based models with both user and ad as input features, allowing for early-stage interaction between these features, are introduced in the ranking stage to mitigate this issue, they are computationally infeasible for the retrieval stage. To bridge this gap, this paper proposes an efficient GPU-based feature interaction for the dual-tower network to significantly improve ret

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylei2025an

Related papers

• Hierarchical Structured Neural Network: Efficient Retrieval Scaling For Large Scale Recommendation (2024)0.00
• Gpu-accelerated Multi-relational Parallel Graph Retrieval For Web-scale Recommendations (2025)0.00
• Recurrent Binary Embedding For Gpu-enabled Exhaustive Retrieval From Billion-scale Semantic Vectors (2018)8.35
• Revisiting Neural Retrieval On Accelerators (2023)9.41
• Deep Retrieval: Learning A Retrievable Structure For Large-scale Recommendations (2020)0.00
• Async Learned User Embeddings For Ads Delivery Optimization (2024)0.00
• Uni-retriever: Towards Learning The Unified Embedding Based Retriever In Bing Sponsored Search (2022)9.92
• Beyond Two-tower Matching: Learning Sparse Retrievable Cross-interactions For Recommendation (2023)7.81