MABLE通过双利普希茨解码，让图嵌入更稳定且可解释。
MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning
- 用掩码重建+余弦相似性约束，对齐增强视图并分散未配对嵌入
- 在铜矿和阿拉伯盾区数据上，嵌入生成的图层与下游任务信号互补
- 无需判别器或难样本选择，适合地质勘探等需可解释性的场景
我们提出MABLE（带双利普希茨解码的掩码自编码用于嵌入与图度量学习），一种从大规模异构图中学习节点和图嵌入的自监督框架，以地理空间矿产勘探数据为例。MABLE结合掩码重构与固定余弦相似性损失，对齐匹配的增强视图，同时保持未配对嵌入充分分散。双利普希茨特征解码器将每个节点嵌入的低维重构部分与特征相似性关联，而匹配节点一致性塑造图池化使用的剩余上下文。利普希茨控制的池化在保留节点嵌入扰动下稳定图级表示，而增强对齐训练了对掩码、节点删除和采样变化的鲁棒性。在局部铜矿和区域阿拉伯盾区研究中，MABLE嵌入提供了互补的下游信号，并生成了可用于假设生成的一致嵌入衍生图层，无需学习判别器或硬负样本选择。
原文摘要 · Abstract (English)
We propose MABLE (Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning), a self-supervised framework for learning node and graph embeddings from large, heterogeneous graphs, demonstrated here on geospatial mineral-exploration data. MABLE combines masked reconstruction with fixed cosine-similarity losses that align matched augmented views while keeping unpaired embeddings well spread. A bi-Lipschitz feature decoder ties a low-dimensional reconstruction component of each node embedding to feature similarity, while matched-node consistency shapes the remaining context used by graph pooling. Lipschitz-controlled pooling helps stabilize graph-level representations under perturbations of retained node embeddings, while augmentation alignment trains robustness to masking, node dropping, and sampling variation. Across local copper and regional Arabian Shield studies, MABLE embeddings provide complementary downstream signal and produce coherent embedding-derived layers for hypothesis generation without learned discriminators or hard-negative selection.
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。