RELATE: A Schema-Agnostic Perceiver Encoder for Multimodal Relational Graphs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914132118208512 |
|---|---|
| author | Meyer, Joe Lachi, Divyansha Mohammadi, Mahmoud Upendra, Roshan Reddy Dyer, Eva L. Li, Mark Palczewski, Tom |
| author_facet | Meyer, Joe Lachi, Divyansha Mohammadi, Mahmoud Upendra, Roshan Reddy Dyer, Eva L. Li, Mark Palczewski, Tom |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19954 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RELATE: A Schema-Agnostic Perceiver Encoder for Multimodal Relational Graphs Meyer, Joe Lachi, Divyansha Mohammadi, Mahmoud Upendra, Roshan Reddy Dyer, Eva L. Li, Mark Palczewski, Tom Artificial Intelligence Databases Machine Learning 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. |
| title | RELATE: A Schema-Agnostic Perceiver Encoder for Multimodal Relational Graphs |
| topic | Artificial Intelligence Databases Machine Learning |
| url | https://arxiv.org/abs/2510.19954 |