发表机构
IDEAS Research Institute（IDEAS 研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出GeoGAE，一种基于超球云表示的自编码器，通过Transformer实现图级嵌入与重建，解决现有方法可扩展性问题，并在多领域数据集上验证有效性。
AI 中文摘要
将结构化对象嵌入到欧几里得空间中已经促成了广泛的成功机器学习应用。这些对象包括单词、文档、图像块、时间序列和图节点。相比之下，嵌入整个图仍然是一个具有挑战性的问题。现有方法要么保持图节点的原始顺序，要么将输出节点与输入节点匹配，这两种方法都会产生可扩展性问题。在这项工作中，我们提出了一种将图表示为超球云的方法，这使得我们能够定义一个特定的、通常是唯一的节点排序。基于这种表示，我们提出了GeoGAE，一种自编码器，其中Transformer编码器将超球云转换为图级嵌入，而Transformer解码器将图级嵌入转换回图。这种公式使模型能够同时捕获全局图结构和局部关系模式。我们在多个跨越不同领域的图数据集上评估了我们的方法。结果表明，我们的方法在从嵌入中编码和重建图方面是有效的。
英文摘要
Embedding structured objects into Euclidean spaces has enabled a wide range of successful machine learning applications. Such objects include words, documents, image patches, time series, and graph nodes. In contrast, embedding entire graphs remains a challenging problem. Existing methods either sustain the original order of the graph nodes or match the output nodes to the input ones, both of which create scalability issues. In this work, we propose a graph representation as a cloud of hyperballs, which allows us to define a specific, typically unique, node ordering. Based on this representation, we propose GeoGAE, an autoencoder, in which the Transformer encoder translates a hyperball cloud into a graph-level embedding, and the Transformer decoder translates the graph-level embedding back into the graph. This formulation enables the model to capture both the global graph structure and local relational patterns. We evaluate our method on multiple graph datasets, spanning various domains. The results demonstrate effectiveness of our method in encoding and reconstructing graphs from their embeddings.
CommentsSubmitted for ICLR 2027
