通过高斯过程的高效图压缩
Efficient Graph Condensation via Gaussian Process
AI总结:
提出基于高斯过程的图压缩方法GCGP,避免双层优化,利用协方差函数和Concrete松弛高效压缩大规模图并保持性能。
摘要:
图压缩在保持性能的同时减小大型图的规模,解决了图神经网络因大型数据集上的计算效率低下而带来的可扩展性挑战。现有方法通常依赖双层优化,需要大量的GNN训练,限制了其可扩展性。为解决这些问题,本文提出了一种新颖且计算高效的图压缩方法——通过高斯过程的图压缩(GCGP)。GCGP利用高斯过程(GP),以压缩图作为观测值,来估计预测的后验分布。这种方法无需GNN通常所需的迭代且资源密集的训练。为了增强GCGP捕获函数值之间依赖关系的能力,我们推导了一个结合结构信息的专门协方差函数。该协方差函数通过局部邻域聚合拓宽了输入节点的感受野,从而有助于表示节点内复杂的依赖关系。为了解决压缩图中二元结构信息优化的挑战,使用Concrete随机变量将二元邻接矩阵近似为连续形式。这种松弛过程使得邻接矩阵能够以可微的形式表示,从而能够将基于梯度的优化技术应用于离散图结构。实验结果表明,所提出的GCGP方法能够高效压缩大规模图数据,同时保持预测性能,解决了可扩展性和效率方面的挑战。我们方法的实现公开于https://github.com/WANGLin0126/GCGP。
英文摘要:
Graph condensation reduces the size of large graphs while preserving performance, addressing the scalability challenges of Graph Neural Networks caused by computational inefficiencies on large datasets. Existing methods often rely on bi-level optimization, requiring extensive GNN training and limiting their scalability. To address these issues, this paper proposes Graph Condensation via Gaussian Process (GCGP), a novel and computationally efficient approach to graph condensation. GCGP utilizes a Gaussian Process (GP), with the condensed graph serving as observations, to estimate the posterior distribution of predictions. This approach eliminates the need for the iterative and resource-intensive training typically required by GNNs. To enhance the capability of the GCGP in capturing dependencies between function values, we derive a specialized covariance function that incorporates structural information. This covariance function broadens the receptive field of input nodes by local neighborhood aggregation, thereby facilitating the representation of intricate dependencies within the nodes. To address the challenge of optimizing binary structural information in condensed graphs, Concrete random variables are utilized to approximate the binary adjacency matrix in a continuous counterpart. This relaxation process allows the adjacency matrix to be represented in a differentiable form, enabling the application of gradient-based optimization techniques to discrete graph structures. Experimental results show that the proposed GCGP method efficiently condenses large-scale graph data while preserving predictive performance, addressing the scalability and efficiency challenges. The implementation of our method is publicly available at https://github.com/WANGLin0126/GCGP.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。