Back to papers
Massively Parallel Algorithms for Personalized PageRank
Summary: Delta-Push is a distributed framework for single-source and top-k Personalized PageRank on massive graphs, merging a redesigned parallel push with pre-sampled random walks to reduce rounds. Using the MPC model, it bounds per-round load by m/p, scales with executors for batched queries, and introduces a friendly top-k algorithm; experiments show improved efficiency over baselines.
(summarized by gpt-5-nano on Feb 09 2026)
- Paper ID
- 12353
- Venue
- VLDB
- Year
- 2021
- Pagerank
- 6.0846728e-05
- Overall Rank
- 4,562 | 68.27%
- DOI
-
10.14778/3461535.3461554
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 11 of 11 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
| 5,147 |
Efficient Tree-SVD for Subset Node Embedding over Large Dynamic Graphs |
2023 |
SIGMOD |
5.6643767e-05 |
| 5,655 |
Personalized PageRank on Evolving Graphs with an Incremental Index-Update Scheme |
2023 |
SIGMOD |
5.387631e-05 |
| 6,381 |
Edge-based Local Push for Personalized PageRank |
2022 |
VLDB |
5.0890757e-05 |
| 9,214 |
Efficient and Accurate PageRank Approximation on Large Graphs |
2024 |
SIGMOD |
4.3716847e-05 |
| 9,325 |
Efficient Personalized PageRank Computation: The Power of Variance-Reduced Monte Carlo Approaches |
2023 |
SIGMOD |
4.3556432e-05 |
| 10,044 |
ACGraph: An Efficient Asynchronous Out-of-Core Graph Processing Framework |
2026 |
SIGMOD |
4.1945683e-05 |
| 10,911 |
Topology-aware Parallel Joins |
2024 |
PODS |
4.1945683e-05 |
| 10,925 |
Parallel Communication Obliviousness: One Round and Beyond |
2024 |
PODS |
4.1945683e-05 |
| 10,958 |
Efficient Approximation of Kemeny’s Constant for Large Graphs |
2024 |
SIGMOD |
4.1945683e-05 |
| 11,186 |
Effective and Efficient PageRank-based Positioning for Graph Visualization |
2023 |
SIGMOD |
4.1945683e-05 |
| 11,217 |
Efficient Approximation Framework for Attribute Recommendation |
2023 |
SIGMOD |
4.1945683e-05 |
Outgoing Citations (Sorted by Pagerank)
Showing 13 of 13 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 886 |
Fast Personalized PageRank on MapReduce |
2011 |
SIGMOD |
0.00015597161 |
| 1,411 |
Communication Steps for Parallel Query Processing |
2013 |
PODS |
0.0001212565 |
| 1,821 |
Computing Personalized PageRank Quickly by Exploiting Graph Structures |
2014 |
VLDB |
0.00010423565 |
| 2,098 |
Efficient Ad-hoc Search for Personalized PageRank |
2013 |
SIGMOD |
9.5480012e-05 |
| 2,210 |
BEAR: Block Elimination Approach for Random Walk with Restart on Large Graphs |
2015 |
SIGMOD |
9.2856573e-05 |
| 2,242 |
HubPPR: Effective Indexing for Approximate Personalized PageRank |
2017 |
VLDB |
9.218875e-05 |
| 2,537 |
BePI: Fast and Memory-Efficient Method for Billion-Scale Random Walk with Restart |
2017 |
SIGMOD |
8.5834428e-05 |
| 2,780 |
Incremental and Accuracy-Aware Personalized PageRank through Scheduled Approximation |
2013 |
VLDB |
8.1317773e-05 |
| 3,872 |
Distributed Algorithms on Exact Personalized PageRank |
2017 |
SIGMOD |
6.6785582e-05 |
| 4,733 |
TopPPR: Top-k Personalized PageRank Queries with Precision Guarantees on Large Graphs |
2018 |
SIGMOD |
5.9631943e-05 |
| 5,226 |
Link Spam Detection Based on Mass Estimation |
2006 |
VLDB |
5.6187905e-05 |
| 6,309 |
Efficient Algorithms for Finding Approximate Heavy Hitters in Personalized PageRanks |
2018 |
SIGMOD |
5.1167347e-05 |
| 8,236 |
PRSim: Sublinear Time SimRank Computation on Large Power-Law Graphs |
2019 |
SIGMOD |
4.553296e-05 |
Semantically Similar Papers