用符号化向量传递实现可解释的图分类，效果媲美神经网络。
Symbolic Graph Intelligence: Hypervector Message Passing for Learning Graph-Level Patterns with Tsetlin Machines
- 通过分层绑定节点、边和属性信息生成符号化超向量。
- 在TUDataset上达到与神经网络相当的准确率，且结果可解释。
- 适合需要透明决策过程的图学习场景，如医疗或金融分析。
我们提出一种多层符号化框架，用于通用图分类，利用稀疏二进制超向量和刘特林机（Tsetlin Machines）。每个图通过结构化消息传递编码，将节点、边和属性信息绑定并打包为符号化超向量。该过程通过从节点属性到边关系再到结构角色的分层绑定，保留了图的层次语义，生成紧凑、离散的表示。我们还构建了一个局部可解释性框架，使该方法具备关键优势：局部可解释性。我们在TUDataset基准上验证了该方法，在保持强符号透明性的同时，实现了与神经图模型相媲美的竞争性准确率。
原文摘要 · Abstract (English)
We propose a multilayered symbolic framework for general graph classification that leverages sparse binary hypervectors and Tsetlin Machines. Each graph is encoded through structured message passing, where node, edge, and attribute information are bound and bundled into a symbolic hypervector. This process preserves the hierarchical semantics of the graph through layered binding from node attributes to edge relations to structural roles resulting in a compact, discrete representation. We also formulate a local interpretability framework which lends itself to a key advantage of our approach being locally interpretable. We validate our method on TUDataset benchmarks, demonstrating competitive accuracy with strong symbolic transparency compared to neural graph models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。