paper-with-me

홈 › Papers

FIT-GNN: Faster Inference Time for GNNs Using Coarsening

2024-10-19 · Shubhajit Roy, Hrriday Ruparel, Kishan Ved, Anirban Dasgupta

Scalability of Graph Neural Networks (GNNs) remains a significant challenge, particularly when dealing with large-scale graphs. To tackle this, coarsening-based methods are used to reduce the graph into a smaller graph, resulting in faster computation. Nonetheless, prior research has not adequately addressed the computational costs during the inference phase. This paper presents a novel approach to improve the scalability of GNNs by reducing computational burden during both training and inference phases. We demonstrate two different methods (Extra-Nodes and Cluster-Nodes). Our study also proposes a unique application of the coarsening algorithm for graph-level tasks, including graph classification and graph regression, which have not yet been explored. We conduct extensive experiments on multiple benchmark datasets in the order of $100K$ nodes to evaluate the performance of our approach. The results demonstrate that our method achieves competitive performance in tasks involving classification and regression on nodes and graphs, compared to traditional GNNs, while having single-node inference times that are orders of magnitude faster. Furthermore, our approach significantly reduces memory consumption, allowing training and inference on low-resource devices where traditional methods struggle.

📄 PDF Abstract BibTeX arXiv:2410.15001

Code (1)

Roy-Shubhajit/FIT-GNN 공식 구현 pytorch

Tasks

ClassificationGraph ClassificationGraph RegressionNode ClassificationNode Regressionregression

Similar Papers 제목 키워드 기반

Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training

2024-12-18 · Shuyin Xia, Xinjun Ma, Zhiyuan Liu, Cheng Liu 외

Graph Neural Networks (GNNs) have demonstrated significant achievements in processing graph data, yet scalability remains a substantial challenge. To address this, numerous graph coarsening methods have been developed. H…

Graph Neural Network

Graph Coarsening with Message-Passing Guarantees

2024-05-28 · Antonin Joly, Nicolas Keriven

Graph coarsening aims to reduce the size of a large graph while preserving some of its key properties, which has been used in many applications to reduce computational load and memory footprint. For instance, in graph ma…

Node Classification

Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms

2026-01-30 · Xiang Wu, Rong-Hua Li, Xunkai Li, Kangfei Zhao 외 arxiv

Graph coarsening reduces the size of a graph while preserving certain properties. Most existing methods preserve either spectral or spatial characteristics. Recent research shows that topology-preserving coarsening metho…

Node Classification

Scaling Up Graph Neural Networks Via Graph Coarsening

2021-06-09 · Zengfeng Huang, Shengzhong Zhang, Chong Xi, Tang Liu 외

Scalability of graph neural networks remains one of the major challenges in graph machine learning. Since the representation of a node is computed by recursively aggregating and transforming representation vectors of its…

Stochastic Optimization

CTS-Bench: Benchmarking Graph Coarsening Trade-offs for GNNs in Clock Tree Synthesis

2026-02-22 · Barsat Khadka, Kawsher Roxy, Md Rubel Ahmed arxiv

Graph Neural Networks (GNNs) are increasingly explored for physical design analysis in Electronic Design Automation, particularly for modeling Clock Tree Synthesis behavior such as clock skew and buffering complexity. Ho…

Computational EfficiencyGraph Clustering