GDPool 提出图依赖池化方法，让层次图神经网络自适应确定池化粒度
Graph-dependent pooling: adaptive granularity in hierarchical graph neural networks
AI 导读
研究者提出 Graph-Dependent Pooling（GDPool），为每个图动态决定层次图神经网络中的池化粒度，摆脱以往预定义簇数或固定池化比例的限制。该方法通过梯度对齐分析层级目标间的优化冲突，并利用自注意力选择结构上重要的节点作为锚点、以软节点分配构建粗化图。在金属有机框架和分子图基准上，GDPool 均取得最佳预测性能，模块度持续高于现有方法。
正文 · 原文
Abstract:Graph Neural Networks are widely used to learn structural representations of relational data. Hierarchical graph pooling learns multi-level representations by progressively coarsening graphs; however, prior methods rely on predefined cluster numbers or fixed pooling ratios, limiting adaptability to individual graphs. We propose Graph-Dependent Pooling (GDPool), which dynamically determines pooling granularity for each graph. We analyze optimization conflicts among layer-wise objectives through gradient alignment, showing that independently supervised pooling levels can send conflicting gradients to shared parameters. GDPool uses self-attention to select graph-specific anchors representing structurally important nodes and constructs coarse graphs through soft node assignment. Experiments on metal-organic framework and molecular graph benchmarks show that GDPool consistently achieves the best predictive performance across all benchmarks. Evaluations using modularity and the effective number of clusters show that GDPool achieves consistently higher modularity than existing methods while the number of active clusters decreases monotonically with depth. Sensitivity analyses confirm stable behavior across hyperparameter and architectural choices.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.33623 [cs.AI] |
| (or arXiv:2610.33623v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33623 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hyejin Jang [view email]
[v1]
Sat, 24 Oct 2026 11:54:16 UTC (1,966 KB)
来源：arXiv cs.AI · arxiv.org