graph partitioning
57 papers with code • 1 benchmarks • 2 datasets
Graph Partitioning is generally the first step of distributed graph computing tasks. The targets are load-balance and minimizing the communication volume.
Libraries
Use these libraries to find graph partitioning models and implementations
HAM
Latest papers with no code
CATGNN: Cost-Efficient and Scalable Distributed Training for Graph Neural Networks
Existing distributed systems load the entire graph in memory for graph partitioning, requiring a huge memory space to process large graphs and thus hindering GNN training on such large graphs using commodity workstations.
A Clustering Method with Graph Maximum Decoding Information
Despite its efficacy, the current clustering method utilizing the graph-based model overlooks the uncertainty associated with random walk access between nodes and the embedded structural information in the data.
Unsupervised Optimisation of GNNs for Node Clustering
Although modularity is a graph partitioning quality metric, we show that this can be used to optimise GNNs that also encode features without a drop in performance.
An Effective Branch-and-Bound Algorithm with New Bounding Methods for the Maximum $s$-Bundle Problem
Exact algorithms for MBP mainly follow the branch-and-bound (BnB) framework, whose performance heavily depends on the quality of the upper bound on the cardinality of a maximum s-bundle and the initial lower bound with graph reduction.
Circuit Partitioning for Multi-Core Quantum Architectures with Deep Reinforcement Learning
Quantum computing holds immense potential for solving classically intractable problems by leveraging the unique properties of quantum mechanics.
GLISP: A Scalable GNN Learning System by Exploiting Inherent Structural Properties of Graphs
As a powerful tool for modeling graph data, Graph Neural Networks (GNNs) have received increasing attention in both academia and industry.
Large Scale Training of Graph Neural Networks for Optimal Markov-Chain Partitioning Using the Kemeny Constant
In this work, we propose several GNN-based architectures to tackle the graph partitioning problem for Markov Chains described as kinetic networks.
Uplifting the Expressive Power of Graph Neural Networks through Graph Partitioning
In this work, we study the expressive power of graph neural networks through the lens of graph partitioning.
A Novel Differentiable Loss Function for Unsupervised Graph Neural Networks in Graph Partitioning
However, these methods face significant hurdles: supervised learning is constrained by the necessity of labeled solution instances, which are often computationally impractical to obtain; reinforcement learning grapples with instability in the learning pro-cess; and unsupervised learning contends with the absence of a differentia-ble loss function, a consequence of the discrete nature of most combinatorial optimization problems.
NeuroCUT: A Neural Approach for Robust Graph Partitioning
Second, we decouple the parameter space and the partition count making NeuroCUT inductive to any unseen number of partition, which is provided at query time.
