Pith. sign in

REVIEW 7 cited by

Supervised Learning on Relational Databases with Graph Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2002.02046 v1 pith:MH2PQM2J submitted 2020-02-06 cs.LG cs.AIcs.DBstat.ML

Milan Cvitkovic This is my paper · ORCID
classification cs.LGcs.AIcs.DBstat.ML
keywords datarelationallearningdatabaseseffortsengineeringfeaturegraph
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The majority of data scientists and machine learning practitioners use relational data in their work [State of ML and Data Science 2017, Kaggle, Inc.]. But training machine learning models on data stored in relational databases requires significant data extraction and feature engineering efforts. These efforts are not only costly, but they also destroy potentially important relational structure in the data. We introduce a method that uses Graph Neural Networks to overcome these challenges. Our proposed method outperforms state-of-the-art automatic feature engineering methods on two out of three datasets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Parameter-Free Encoders Remain Viable for RDB Foundation Models

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Trainable RDB encoders cannot robustly exploit neighborhood labels as fixed foundation-model features or feature-importance signals, so simple parameter-free encoders stay near-SOTA.

  2. A Fair Benchmarking of Deep Relational Database Learning Models

    cs.DB 2026-07 conditional novelty 6.0 of 10

    Under a unified protocol on five RelBench databases, the Relational Transformer outperforms graph-based RDB models and TabPFN 2.5, with multi-hop gains that shrink relative to training cost.

  3. No Need to Train Your RDB Foundation Model

    cs.AI 2026-02 conditional novelty 6.0 of 10

    Column-wise, parameter-free JUICE encodings let single-table ICL models solve multi-table RDB prediction tasks with no training or fine-tuning.

  4. Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databases

    cs.DB 2025-08 unverdicted novelty 5.0 of 10

    SRP combines feature synthesis, cross-table retrieval, and graph propagation to improve predictive modeling on relational databases.

  5. Rel-HNN: Split Parallel Hypergraph Neural Network for Learning on Relational Databases

    cs.DB 2025-07 reject novelty 5.0 of 10

    Rel-HNN models each tuple as a hyperedge over attribute-value nodes and reports large accuracy gains, but its hypergraph construction appears to include the target label as an input node.

  6. From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNs

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Selective task-aware attribute promotion into graph nodes improves GNN classification on relational and tabular data compared to schema-based and heuristic graph construction.

  7. Graph-Based Feature Augmentation for Predictive Tasks on Relational Datasets

    cs.DB 2025-08 conditional novelty 4.0 of 10

    ReCoGNN automatically augments a base table with task-relevant features from related relational tables by splitting attributes into semantic sub-tables and propagating information through a weighted heterogeneous graph.

Pith tools