REVIEW 11 cited by
Relational Deep Learning: Graph Representation Learning on Relational Databases
Not yet reviewed by Pith; the record is open.
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
Relational Deep Learning: Graph Representation Learning on Relational Databases
read the original abstract
Much of the world's most valued data is stored in relational databases and data warehouses, where the data is organized into many tables connected by primary-foreign key relations. However, building machine learning models using this data is both challenging and time consuming. The core problem is that no machine learning method is capable of learning on multiple tables interconnected by primary-foreign key relations. Current methods can only learn from a single table, so the data must first be manually joined and aggregated into a single training table, the process known as feature engineering. Feature engineering is slow, error prone and leads to suboptimal models. Here we introduce an end-to-end deep representation learning approach to directly learn on data laid out across multiple tables. We name our approach Relational Deep Learning (RDL). The core idea is to view relational databases as a temporal, heterogeneous graph, with a node for each row in each table, and edges specified by primary-foreign key links. Message Passing Graph Neural Networks can then automatically learn across the graph to extract representations that leverage all input data, without any manual feature engineering. Relational Deep Learning leads to more accurate models that can be built much faster. To facilitate research in this area, we develop RelBench, a set of benchmark datasets and an implementation of Relational Deep Learning. The data covers a wide spectrum, from discussions on Stack Exchange to book reviews on the Amazon Product Catalog. Overall, we define a new research area that generalizes graph machine learning and broadens its applicability to a wide set of AI use cases.
Forward citations
Cited by 11 Pith papers
-
Joint Relational Database Generation via Graph-Conditional Diffusion Models
GRDM jointly generates relational database tables via graph-conditional diffusion without table ordering, outperforming autoregressive baselines on multi-hop correlations and single-table fidelity across six real RDBs.
-
Parameter-Free Encoders Remain Viable for RDB Foundation Models
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.
-
GNBAN: Graph Neural Basis Attention Networks for Long-Horizon Forecasting over Large Entity Sets
GNBAN combines heterogeneous graph representation learning with a basis-decomposition head and per-basis attention to achieve 4-5% better WRMSSE on large retail forecasting benchmarks while exposing demand drivers.
-
A Fair Evaluation of Graph Foundation Models for Node Property Prediction
Reevaluation of 9 GFMs shows only recent prior-data fitted network models outperform tuned GNNs on node property prediction, at higher cost.
-
RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases
RelPrism generates self-supervised pseudo-tasks from three attribute perspectives via multi-granularity clustering to improve representation learning for relational database prediction tasks.
-
UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure
UniSAGE jointly models static and dynamic attributes in a single attribute graph and improves entity classification/regression over prior RDL and GNN baselines.
-
No Need to Train Your RDB Foundation Model
Column-wise, parameter-free JUICE encodings let single-table ICL models solve multi-table RDB prediction tasks with no training or fine-tuning.
-
Parameter-Free Encoders Remain Viable for RDB Foundation Models
A parameter-free relational encoder combined with a single-table foundation model matches or beats parameterized, pre-trained RDB encoders on six benchmarks.
-
The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning
Introduces curvature-stratified evaluation showing relational learning model rankings are stable within curvature regimes but shift across them, making performance geometry-dependent.
-
SemStruct: Contextualizing Semantic Embeddings with Structural Information for Schema Matching
SemStruct models tables as heterogeneous graphs with GNNs on frozen PLM embeddings to incorporate row co-occurrences for schema matching and reports SOTA results on Valentine and SOTAB-SM benchmarks.
-
Retrieval-Augmented Generation with Graphs (GraphRAG)
A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.