RELATE: A Schema-Agnostic Cross-Attention Encoder for Multimodal Relational Graphs

Joe Meyer, Divyansha Lachi, Mahmoud Mohammadi, Roshan Reddy Upendra, Eva L Dyer, Minghua Li, Tom Palczewski

Keywords: relational deep learning, tabular learning, heterogenous temporal graphs

TL;DR: RELATE is a schema-agnostic encoder that plugs into any GNN.

Abstract: 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 $\textbf{RELATE}$ (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.

Submission Number: 58