GRALE让不同大小图共享嵌入空间，支持复杂图任务预训练。
The quest for the GRAph Level autoEncoder (GRALE)
- 基于Evoformer架构，用可微节点匹配实现图编码解码。
- 在分子数据上验证，支持分类、编辑、插值等多类下游任务。
- 适合需要图生成与操作的科研人员，如药物设计领域。
尽管基于图的学习受到广泛关注，图表示学习仍是具有挑战性的任务，其突破可能影响化学、生物等关键领域。为此，我们提出GRALE，一种新型图自编码器，可将不同尺寸的图映射到共享嵌入空间中进行编码与解码。GRALE采用受最优传输启发的损失函数，通过可微节点匹配模块联合训练编码器与解码器。其注意力架构基于AlphaFold的核心组件Evoformer，并扩展支持图的编码与解码。在模拟数据和分子数据上的数值实验表明，GRALE实现了高度通用的预训练，适用于从分类、回归到图插值、编辑、匹配和预测等多种下游任务。
原文摘要 · Abstract (English)
Although graph-based learning has attracted a lot of attention, graph representation learning is still a challenging task whose resolution may impact key application fields such as chemistry or biology. To this end, we introduce GRALE, a novel graph autoencoder that encodes and decodes graphs of varying sizes into a shared embedding space. GRALE is trained using an Optimal Transport-inspired loss that compares the original and reconstructed graphs and leverages a differentiable node matching module, which is trained jointly with the encoder and decoder. The proposed attention-based architecture relies on Evoformer, the core component of AlphaFold, which we extend to support both graph encoding and decoding. We show, in numerical experiments on simulated and molecular data, that GRALE enables a highly general form of pre-training, applicable to a wide range of downstream tasks, from classification and regression to more complex tasks such as graph interpolation, editing, matching, and prediction.
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。