RobGC: Towards Robust Graph Condensation

• URL: http://arxiv.org/abs/2406.13200v1
• Date: Wed, 19 Jun 2024 04:14:57 GMT
• Title: RobGC: Towards Robust Graph Condensation
• Authors: Xinyi Gao, Hongzhi Yin, Tong Chen, Guanhua Ye, Wentao Zhang, Bin Cui,
• Abstract summary: Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning. However, the increasing prevalence of large-scale graphs presents a significant challenge for GNN training due to their computational demands. We propose graph condensation (GC) to generate an informative compact graph that enables efficient training of GNNs while retaining performance.
• Score: 61.259453496191696
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning. However, the increasing prevalence of large-scale graphs presents a significant challenge for GNN training due to their computational demands, limiting the applicability of GNNs in various scenarios. In response to this challenge, graph condensation (GC) is proposed as a promising acceleration solution, focusing on generating an informative compact graph that enables efficient training of GNNs while retaining performance. Despite the potential to accelerate GNN training, existing GC methods overlook the quality of large training graphs during both the training and inference stages. They indiscriminately emulate the training graph distributions, making the condensed graphs susceptible to noises within the training graph and significantly impeding the application of GC in intricate real-world scenarios. To address this issue, we propose robust graph condensation (RobGC), a plug-and-play approach for GC to extend the robustness and applicability of condensed graphs in noisy graph structure environments. Specifically, RobGC leverages the condensed graph as a feedback signal to guide the denoising process on the original training graph. A label propagation-based alternating optimization strategy is in place for the condensation and denoising processes, contributing to the mutual purification of the condensed graph and training graph. Additionally, as a GC method designed for inductive graph inference, RobGC facilitates test-time graph denoising by leveraging the noise-free condensed graph to calibrate the structure of the test graph. Extensive experiments show that RobGC is compatible with various GC methods, significantly boosting their robustness under different types and levels of graph structural noises.

Related papers

• GC-Bench: An Open and Unified Benchmark for Graph Condensation [54.70801435138878]
  We develop a comprehensive Graph Condensation Benchmark (GC-Bench) to analyze the performance of graph condensation. GC-Bench systematically investigates the characteristics of graph condensation in terms of the following dimensions: effectiveness, transferability, and complexity. We have developed an easy-to-use library for training and evaluating different GC methods to facilitate reproducible research.
  arXiv  Detail & Related papers  (2024-06-30T07:47:34Z)
• GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights [30.796414860754837]
  Graph condensation (GC) is an emerging technique designed to learn a significantly smaller graph that retains the essential information of the original graph. This paper introduces textbfGC4NC, a comprehensive framework for evaluating diverse GC methods on node classification. Our systematic evaluation offers novel insights into how condensed graphs behave and the critical design choices that drive their success.
  arXiv  Detail & Related papers  (2024-06-24T15:17:49Z)
• Spectral Greedy Coresets for Graph Neural Networks [61.24300262316091]
  The ubiquity of large-scale graphs in node-classification tasks hinders the real-world applications of Graph Neural Networks (GNNs) This paper studies graph coresets for GNNs and avoids the interdependence issue by selecting ego-graphs based on their spectral embeddings. Our spectral greedy graph coreset (SGGC) scales to graphs with millions of nodes, obviates the need for model pre-training, and applies to low-homophily graphs.
  arXiv  Detail & Related papers  (2024-05-27T17:52:12Z)
• Graph Condensation for Open-World Graph Learning [48.38802327346445]
  Graph condensation (GC) has emerged as a promising acceleration solution for efficiently training graph neural networks (GNNs) Existing GC methods are limited to aligning the condensed graph with merely the observed static graph distribution. In real-world scenarios, however, graphs are dynamic and constantly evolving, with new nodes and edges being continually integrated. We propose OpenGC, a robust GC framework that integrates structure-aware distribution shift to simulate evolving graph patterns.
  arXiv  Detail & Related papers  (2024-05-27T09:47:09Z)
• Simple Graph Condensation [30.85754566420301]
  Graph condensation involves tuning Graph Neural Networks (GNNs) on a small condensed graph for use on a large-scale original graph. We introduce the Simple Graph Condensation (SimGC) framework, which aligns the condensed graph with the original graph from the input layer to the prediction layer. SimGC achieves a significant speedup of up to 10 times compared to existing graph condensation methods.
  arXiv  Detail & Related papers  (2024-03-22T05:04:48Z)
• Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data [91.27527985415007]
  Existing graph condensation methods rely on the joint optimization of nodes and structures in the condensed graph. We advocate a new Structure-Free Graph Condensation paradigm, named SFGC, to distill a large-scale graph into a small-scale graph node set.
  arXiv  Detail & Related papers  (2023-06-05T07:53:52Z)
• Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
  We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN) GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
  arXiv  Detail & Related papers  (2022-05-19T14:08:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.