TinyGraph：面向图神经网络的特征与节点联合压缩
TinyGraph: Joint Feature and Node Condensation for Graph Neural Networks
AI总结：
针对大规模图训练GNN计算成本高、现有节点压缩后特征仍冗余的问题，提出TinyGraph框架，通过梯度匹配同时压缩节点与特征，在大幅缩减规模的同时保留了极高的测试准确率。
摘要：
在大规模图上训练图神经网络（GNN）颇具挑战性，原因是海量节点与高维节点特征会带来极高的计算开销。现有图压缩研究仅通过减少图中节点数量来解决这一问题，但得到的压缩图数据仍然十分臃肿。具体而言，尽管Citeseer数据集的训练节点数被压缩至0.9%（30个节点），但特征数量仍有3703个，远超训练样本的规模。针对这一挑战，我们研究了大规模图中特征与节点的联合压缩问题。该任务的难点主要在于：1）节点特征与图结构相互交织，要求特征压缩求解器具备结构感知能力；2）难以在压缩图中保留有效信息。为应对这些挑战，我们提出了一种新型框架TinyGraph，可同时对图中的特征和节点进行压缩。具体来说，我们将该问题转化为匹配压缩图上训练的GNN权重梯度与原始图上训练得到的梯度，其中特征压缩通过一个可训练函数实现。通过在训练轨迹上最小化匹配损失得到的压缩图，能够保留原始图中的关键信息。我们开展了大量实验以验证所提TinyGraph的有效性。例如，使用TinyGraph训练的GNN在Cora和Citeseer数据集上分别保留了原始测试准确率的98.5%和97.5%，同时节点数量分别显著减少了97.4%和98.2%，两个数据集的特征数量均减少了90.0%。
英文摘要：
Training graph neural networks (GNNs) on large-scale graphs can be challenging due to the high computational expense caused by the massive number of nodes and high-dimensional nodal features. Existing graph condensation studies tackle this problem only by reducing the number of nodes in the graph. However, the resulting condensed graph data can still be cumbersome. Specifically, although the nodes of the Citeseer dataset are reduced to 0.9% (30 nodes) in training, the number of features is 3,703, severely exceeding the training sample magnitude. Faced with this challenge, we study the problem of joint condensation for both features and nodes in large-scale graphs. This task is challenging mainly due to 1) the intertwined nature of the node features and the graph structure calls for the feature condensation solver to be structure-aware; and 2) the difficulty of keeping useful information in the condensed graph. To address these challenges, we propose a novel framework TinyGraph, to condense features and nodes simultaneously in graphs. Specifically, we cast the problem as matching the gradients of GNN weights trained on the condensed graph and the gradients obtained from training over the original graph, where the feature condensation is achieved by a trainable function. The condensed graph obtained by minimizing the matching loss along the training trajectory can henceforth retain critical information in the original graph. Extensive experiments were carried out to demonstrate the effectiveness of the proposed TinyGraph. For example, a GNN trained with TinyGraph retains 98.5% and 97.5% of the original test accuracy on the Cora and Citeseer datasets, respectively, while significantly reducing the number of nodes by 97.4% and 98.2%, and the number of features by 90.0% on both datasets.
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。
