Scaling graph neural networks with approximate pagerank

A Bojchevski, J Gasteiger, B Perozzi, A Kapoor… - Proceedings of the 26th …, 2020 - dl.acm.org
Graph neural networks (GNNs) have emerged as a powerful approach for solving many
network mining tasks. However, learning on large graphs remains a challenge--many …

Centrality measures in complex networks: A survey

A Saxena, S Iyengar - arxiv preprint arxiv:2011.07190, 2020 - arxiv.org
In complex networks, each node has some unique characteristics that define the importance
of the node based on the given application-specific context. These characteristics can be …

Efficient Algorithms for Personalized PageRank Computation: A Survey

M Yang, H Wang, Z Wei, S Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Personalized PageRank (PPR) is a traditional measure for node proximity on large graphs.
For a pair of nodes and, the PPR value equals the probability that an-discounted random …

Topppr: top-k personalized pagerank queries with precision guarantees on large graphs

Z Wei, X He, X **ao, S Wang, S Shang… - Proceedings of the 2018 …, 2018 - dl.acm.org
Personalized PageRank (PPR) is a classic metric that measures the relevance of graph
nodes with respect to a source node. Given a graph G, a source node s, and a parameter k …

A survey of state management in big data processing systems

QC To, J Soto, V Markl - The VLDB Journal, 2018 - Springer
The concept of state and its applications vary widely across big data processing systems.
This is evident in both the research literature and existing systems, such as Apache Flink …

Unifying the global and local approaches: An efficient power iteration with forward push

H Wu, J Gan, Z Wei, R Zhang - … of the 2021 International Conference on …, 2021 - dl.acm.org
Personalized PageRank (PPR) is a critical measure of the importance of a node t to a source
node s in a graph. The Single-Source PPR (SSPPR) query computes the PPR's of all the …

Personalized pagerank to a target node, revisited

H Wang, Z Wei, J Gan, S Wang, Z Huang - Proceedings of the 26th ACM …, 2020 - dl.acm.org
Personalized PageRank (PPR) is a widely used node proximity measure in graph mining
and network analysis. Given a source node s and a target node t, the PPR value π (s, t) …

Realtime top-k personalized pagerank over large graphs on gpus

J Shi, R Yang, T **, X **ao, Y Yang - Proceedings of the VLDB …, 2019 - dl.acm.org
Given a graph G, a source node s∈ G and a positive integer k, a top-k Personalized
PageRank (PPR) query returns the k nodes with the highest PPR values with respect to s …

Distributed PageRank computation with improved round complexities

S Luo, X Wu, B Kao - Information Sciences, 2022 - Elsevier
PageRank is a classic measure that effectively evaluates the importance of nodes in large
graphs. It has been applied in numerous applications spanning data mining, Web …

[PDF][PDF] Is pagerank all you need for scalable graph neural networks

A Bojchevski, J Klicpera, B Perozzi… - ACM KDD, MLG …, 2019 - mlgworkshop.org
Graph neural networks (GNNs) have emerged as a powerful approach for solving many
network mining tasks. However, efficiently utilizing them on web-scale data remains a …