Sign-guided Bipartite Graph Hashing For Hamming Space Search

Abstract

Bipartite graph hashing (BGH) is extensively used for Top-K search in Hamming space at low storage and inference costs. Recent research adopts graph convolutional hashing for BGH and has achieved the state-of-the-art performance. However, the contributions of its various influencing factors to hashing performance have not been explored in-depth, including the same/different sign count between two binary embeddings during Hamming space search (sign property), the contribution of sub-embeddings at each layer (model property), the contribution of different node types in the bipartite graph (node property), and the combination of augmentation methods. In this work, we build a lightweight graph convolutional hashing model named LightGCH by mainly removing the augmentation methods of the state-of-the-art model BGCH. By analyzing the contributions of each layer and node type to performance, as well as analyzing the Hamming similarity statistics at each layer, we find that the actual neighbors

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywu2024sign

Related papers

• Bipartite Graph Convolutional Hashing For Effective And Efficient Top-n Search In Hamming Space (2023)8.82
• Towards Effective Top-n Hamming Search Via Bipartite Graph Contrastive Hashing (2024)6.34
• Deep Hashing For Signed Social Network Embedding (2019)0.00
• HS-GCN: Hamming Spatial Graph Convolutional Networks For Recommendation (2023)11.67
• Comprehensive Graph-conditional Similarity Preserving Network For Unsupervised Cross-modal Hashing (2020)3.14
• Asymmetric Transfer Hashing With Adaptive Bipartite Graph Learning (2022)8.82
• Graphhash: Graph Clustering Enables Parameter Efficiency In Recommender Systems (2024)4.77
• Hashing-accelerated Graph Neural Networks For Link Prediction (2021)11.49