# RELATE: A Schema-Agnostic Perceiver Encoder for Multimodal Relational Graphs

arXiv: https://arxiv.org/abs/2510.19954 · HTML: https://mlsanity.com/paper/2510.19954/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024)
- [Position: Graph Foundation Models are Already Here](https://mlsanity.com/paper/2402.02216/) (2024)
- [XTab: Cross-table Pretraining for Tabular Transformers](https://mlsanity.com/paper/2305.06090/) (2023)
- [Griffin: Towards a Graph-Centric Relational Database Foundation Model](https://mlsanity.com/paper/2505.05568/) (2025)
- [ConTextTab: A Semantics-Aware Tabular In-Context Learner](https://mlsanity.com/paper/2506.10707/) (2025)
- [PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learning](https://mlsanity.com/paper/2404.00776/) (2024)
- [FoNE: Precise Single-Token Number Embeddings via Fourier Features](https://mlsanity.com/paper/2502.09741/) (2025)
- [GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment](https://mlsanity.com/paper/2406.02953/) (2024)
- [GraphFM: A generalist graph transformer that learns transferable representations across diverse domains](https://mlsanity.com/paper/2407.11907/) (2024)
- [PORTAL: Scalable Tabular Foundation Models via Content-Specific Tokenization](https://mlsanity.com/paper/2410.13516/) (2024)

## Built on by (most cited first, 1 of 1)

- [FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks](https://mlsanity.com/paper/2606.30336/) (2026)

## Abstract (arXiv)

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.