Gnn-encoder: Learning A Dual-encoder Architecture Via Graph Neural Networks For Dense Passage Retrieval

Abstract

Recently, retrieval models based on dense representations are dominant in passage retrieval tasks, due to their outstanding ability in terms of capturing semantics of input text compared to the traditional sparse vector space models. A common practice of dense retrieval models is to exploit a dual-encoder architecture to represent a query and a passage independently. Though efficient, such a structure loses interaction between the query-passage pair, resulting in inferior accuracy. To enhance the performance of dense retrieval models without loss of efficiency, we propose a GNN-encoder model in which query (passage) information is fused into passage (query) representations via graph neural networks that are constructed by queries and their top retrieved passages. By this means, we maintain a dual-encoder structure, and retain some interaction information between query-passage pairs in their representations, which enables us to achieve both efficiency and efficacy in passage retrieval.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyliu2022gnn

Related papers

• Improving Dense Passage Retrieval With Multiple Positive Passages (2025)0.00
• Densifying Sparse Representations For Passage Retrieval By Representational Slicing (2021)0.00
• What Are You Token About? Dense Retrieval As Distributions Over The Vocabulary (2022)8.09
• Learning Diverse Document Representations With Deep Query Interactions For Dense Retrieval (2022)2.51
• LIDER: An Efficient High-dimensional Learned Index For Large-scale Dense Passage Retrieval (2022)0.00
• Investigating Multi-layer Representations For Dense Passage Retrieval (2025)0.00
• Contextualized Query Embeddings For Conversational Search (2021)10.21
• Empowering Dual-encoder With Query Generator For Cross-lingual Dense Retrieval (2023)6.34