CSMF: Cascaded Selective Mask Fine-tuning For Multi-objective Embedding-based Retrieval

Abstract

Multi-objective embedding-based retrieval (EBR) has become increasingly critical due to the growing complexity of user behaviors and commercial objectives. While traditional approaches often suffer from data sparsity and limited information sharing between objectives, recent methods utilizing a shared network alongside dedicated sub-networks for each objective partially address these limitations. However, such methods significantly increase the model parameters, leading to an increased retrieval latency and a limited ability to model causal relationships between objectives. To address these challenges, we propose the Cascaded Selective Mask Fine-Tuning (CSMF), a novel method that enhances both retrieval efficiency and serving performance for multi-objective EBR. The CSMF framework selectively masks model parameters to free up independent learning space for each objective, leveraging the cascading relationships between objectives during the sequential fine-tuning. Without increasing net

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydeng2025csmf

Related papers

• CPS-MEBR: Click Feedback-aware Web Page Summarization For Multi-embedding-based Retrieval (2022)0.00
• Divide And Conquer: Towards Better Embedding-based Retrieval For Recommender Systems From A Multi-task Perspective (2023)7.16
• Event-enhanced Retrieval In Real-time Search (2024)0.95
• MRSE: An Efficient Multi-modality Retrieval System For Large Scale E-commerce (2024)0.00
• Robust Training Objectives Improve Embedding-based Retrieval In Industrial Recommendation Systems (2024)0.00
• Comparing Neighbors Together Makes It Easy: Jointly Comparing Multiple Candidates For Efficient And Effective Retrieval (2024)4.52
• Pebr: A Probabilistic Approach To Embedding Based Retrieval (2024)0.00
• CSMCIR: Cot-enhanced Symmetric Alignment With Memory Bank For Composed Image Retrieval (2026)0.00