Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917543664418816 |
|---|---|
| author | Yin, Jun Huo, Peng Zhu, Bangguo Yan, Hao Wang, Senzhang Pan, Shirui Zhang, Chengqi |
| author_facet | Yin, Jun Huo, Peng Zhu, Bangguo Yan, Hao Wang, Senzhang Pan, Shirui Zhang, Chengqi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07916 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases Yin, Jun Huo, Peng Zhu, Bangguo Yan, Hao Wang, Senzhang Pan, Shirui Zhang, Chengqi Artificial Intelligence Databases Machine Learning 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. |
| title | Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases |
| topic | Artificial Intelligence Databases Machine Learning |
| url | https://arxiv.org/abs/2603.07916 |