Affiliation:
1. Nanyang Technological University, Singapore
Abstract
In bipartite graph analysis, similarity measures play a pivotal role in various applications. Among existing metrics, the Bidirectional Hidden Personalized PageRank (BHPP) stands out for its superior query quality. However, the computational expense of BHPP remains a bottleneck. Existing approximation methods either demand significant matrix storage or incur prohibitive time costs. For example, current state-of-the-art methods require over 3 hours to process a single-source BHPP query on the real-world bipartite graph
Orkut
, which contains approximately 3 × 10
8
edges.
We introduce BIRD, a novel algorithm designed for answering single-source BHPP queries on weighted bipartite graphs. Through meticulous theoretical analysis, we demonstrate that BIRD significantly improves time complexity to
Õ
(
n
), as compared to the previous best one,
Õ
(
m
), under typical relative error setting and constant failure probability. (
n, m
denote the number of nodes and edges respectively.) Extensive experiments confirm that BIRD outperforms existing baselines by orders of magnitude in large-scale bipartite graphs. Notably, our proposed method accomplishes a single-source BHPP query on
Orkut
using merely 7 minutes.
Publisher
Association for Computing Machinery (ACM)
Reference65 articles.
1. [n.d.]. https://drive.google.com/file/d/1s0D8yT9RSIKKzJynh34H9uEogUUB6_7A/view?usp=sharing.
2. 2003. MovieLens 1M Dataset. https://grouplens.org/datasets/movielens.
3. 2006. AOL Query Logs. http://www.cim.mcgill.ca/~dudek/206/Logs/AOL-user-ct-collection.
4. 2010. Last.fm Dataset Version 1.2. http://ocelma.net/MusicRecommendationDataset/lastfm-360K.html.
5. 2012. KDD Cup 2012 Track 2. https://www.kaggle.com/c/kddcup2012-track2.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Topology-monitorable Contrastive Learning on Dynamic Graphs;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24