{"ID":2851885,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.19954","arxiv_id":"2510.19954","title":"RELATE: A Schema-Agnostic Perceiver Encoder for Multimodal Relational Graphs","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 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.","short_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 eac...","url_abs":"https://arxiv.org/abs/2510.19954","url_pdf":"https://arxiv.org/pdf/2510.19954v3","authors":"[\"Joe Meyer\",\"Divyansha Lachi\",\"Mahmoud Mohammadi\",\"Roshan Reddy Upendra\",\"Eva L. Dyer\",\"Mark Li\",\"Tom Palczewski\"]","published":"2025-10-22T18:27:49Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.DB\",\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false}