arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2408.09239cs.IRcs.AI
收藏

通过二分图对比哈希实现高效的Top-N汉明搜索

Towards Effective Top-N Hamming Search via Bipartite Graph Contrastive Hashing

The Chinese University of Hong Kong(香港中文大学);Ocean University of China(中国海洋大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

Yankai Chen, Yixiang Fang, Yifei Zhang, Chenhao Ma, Yang Hong, Irwin King

AI总结:

针对二分图Top-N汉明搜索中现有哈希方法性能衰减的问题,提出BGCH+方法,通过双重自监督增强策略生成更优哈希码,在六个基准上验证了效果提升。

摘要:

二分图上的搜索是推荐系统、数据库检索、文档查询等各类现实应用的基础任务。传统方法依赖向量化节点嵌入在连续欧氏空间中的相似度匹配。为高效处理密集的相似度计算,面向图结构数据的哈希技术已成为重要研究方向。然而,尽管现有研究在汉明空间中具备检索效率,却遭遇了灾难性的性能衰减。为应对这一挑战,我们研究了结合图卷积网络的哈希问题,以实现高效的Top-N搜索。我们的研究结果表明,相较于仅将哈希作为输出嵌入的后处理步骤,在二分图感受野的探索过程中整合哈希技术具备更优的学习效果。为进一步提升模型性能,我们基于上述发现提出了二分图对比哈希方法(Bipartite Graph Contrastive Hashing, BGCH+)。BGCH+引入了一种新颖的双重增强策略,同时对潜在特征空间中的中间信息和哈希码输出进行增强,从而在双重自监督学习范式下生成更具表达力、更鲁棒的哈希码。在六个真实世界基准数据集上的综合实证分析验证了,与现有方法相比,我们的双重特征对比学习能够有效提升BGCH+的性能。

英文摘要:

Searching on bipartite graphs serves as a fundamental task for various real-world applications, such as recommendation systems, database retrieval, and document querying. Conventional approaches rely on similarity matching in continuous Euclidean space of vectorized node embeddings. To handle intensive similarity computation efficiently, hashing techniques for graph-structured data have emerged as a prominent research direction. However, despite the retrieval efficiency in Hamming space, previous studies have encountered catastrophic performance decay. To address this challenge, we investigate the problem of hashing with Graph Convolutional Network for effective Top-N search. Our findings indicate the learning effectiveness of incorporating hashing techniques within the exploration of bipartite graph reception fields, as opposed to simply treating hashing as post-processing to output embeddings. To further enhance the model performance, we advance upon these findings and propose Bipartite Graph Contrastive Hashing (BGCH+). BGCH+ introduces a novel dual augmentation approach to both intermediate information and hash code outputs in the latent feature spaces, thereby producing more expressive and robust hash codes within a dual self-supervised learning paradigm. Comprehensive empirical analyses on six real-world benchmarks validate the effectiveness of our dual feature contrastive learning in boosting the performance of BGCH+ compared to existing approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑