# Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases

arXiv: https://arxiv.org/abs/2603.07916 · HTML: https://mlsanity.com/paper/2603.07916/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Lipschitz regularity of deep neural networks: analysis and efficient estimation](https://mlsanity.com/paper/1805.10965/) (2018)
- [Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free](https://mlsanity.com/paper/2505.06708/) (2025)
- [A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources](https://mlsanity.com/paper/2011.14867/) (2020)
- [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024)
- [RelGNN: Composite Message Passing for Relational Deep Learning](https://mlsanity.com/paper/2502.06784/) (2025)
- [Griffin: Towards a Graph-Centric Relational Database Foundation Model](https://mlsanity.com/paper/2505.05568/) (2025)
- [Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data](https://mlsanity.com/paper/2510.06377/) (2025)
- [Relational Graph Transformer](https://mlsanity.com/paper/2505.10960/) (2025)
- [PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learning](https://mlsanity.com/paper/2404.00776/) (2024)
- [LTE4G: Long-Tail Experts for Graph Neural Networks](https://mlsanity.com/paper/2208.10205/) (2022)
- [Class-Imbalanced Learning on Graphs: A Survey](https://mlsanity.com/paper/2304.04300/) (2023)
- [When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning](https://mlsanity.com/paper/2410.09132/) (2024)
- [Network Embedding with Completely-imbalanced Labels](https://mlsanity.com/paper/2007.03545/) (2020)
- [Graph Neural Network with Curriculum Learning for Imbalanced Node Classification](https://mlsanity.com/paper/2202.02529/) (2022)
- [GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification](https://mlsanity.com/paper/2302.12814/) (2023)
- [GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2306.09612/) (2023)
- [Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition](https://mlsanity.com/paper/2310.18765/) (2023)
- [4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs](https://mlsanity.com/paper/2404.18209/) (2024)

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

- [Incremental Evaluation and Training in Relational Deep Learning](https://mlsanity.com/paper/2608.13023/) (2026)

## Abstract (arXiv)

In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to structure the RDB as a heterogeneous entity graph and adopt the graph neural network (GNN) as the predictive model. However, existing RDL methods neglect the imbalance problem of relational data in RDBs and risk under-representing the minority entities, leading to an unusable model in practice. In this work, we investigate, for the first time, class imbalance problem in RDB entity classification and design the relation-centric minority synthetic over-sampling GNN (Rel-MOSS), in order to fill a critical void in the current literature. Specifically, to mitigate the issue of minority-related information being submerged by majority counterparts, we design the relation-wise gating controller to modulate neighborhood messages from each individual relation type. Based on the relational-gated representations, we further propose the relation-guided minority synthesizer for over-sampling, which integrates the entity relational signatures to maintain relational consistency. Extensive experiments on 12 entity classification datasets provide compelling evidence for the superiority of Rel-MOSS, yielding an average improvement of up to 2.46% and 4.00% in terms of Balanced Accuracy and G-Mean, compared with SOTA RDL methods and classic methods for handling class imbalance.