RELATE统一编码多模态关系数据，提升GNN可扩展性。
RELATE: A Schema-Agnostic Perceiver Encoder for Multimodal Relational Graphs
- 用共享模块统一处理各类属性，无需为每种节点设计专用编码器。
- 在多个基准上性能接近专用编码器，参数量减少最多5倍。
- 适合构建跨数据集预训练的通用图神经网络，助力关系数据基础模型。
关系型多表数据在电商、医疗和科研领域常见，可自然表示为具有多模态节点属性的异质时序图。现有图神经网络依赖特定模式的特征编码器，需为每种节点类型和特征列配置独立模块，限制了可扩展性和参数共享。我们提出RELATE（面向类型化实体潜在聚合的关联编码器），一种与模式无关的即插即用特征编码器，可适配任意通用GNN。RELATE采用共享的模态专用编码器处理类别、数值、文本和时间属性，并通过类似Perceiver的交叉注意力模块将特征聚合为固定尺寸、排列不变的节点表示。我们在ReLGNN和HGT的RelBench基准上评估RELATE，性能达到专用编码器的97%以内，参数量最高减少5倍。该设计支持不同模式，推动多数据集预训练，为关系图数据的基础模型铺平道路。
原文摘要 · Abstract (English)
Relational multi-table data is common in domains such as e-commerce, healthcare, and scientific research, and can be naturally represented as heterogeneous temporal graphs with multi-modal node attributes. Existing graph neural networks (GNNs) rely on schema-specific feature encoders, requiring separate modules for each node type and feature column, which hinders scalability and parameter sharing. We introduce RELATE (Relational Encoder for Latent Aggregation of Typed Entities), a schema-agnostic, plug-and-play feature encoder that can be used with any general purpose GNN. RELATE employs shared modality-specific encoders for categorical, numerical, textual, and temporal attributes, followed by a Perceiver-style cross-attention module that aggregates features into a fixed-size, permutation-invariant node representation. We evaluate RELATE on ReLGNN and HGT in the RelBench benchmark, where it achieves performance within 3% of schema-specific encoders while reducing parameter counts by up to 5x. This design supports varying schemas and enables multi-dataset pretraining for general-purpose GNNs, paving the way toward foundation models for relational graph data.
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。