REVIEW 9 cited by
RelGNN: Composite Message Passing for Relational Deep Learning
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
RelGNN: Composite Message Passing for Relational Deep Learning
read the original abstract
Predictive tasks on relational databases are critical in real-world applications spanning e-commerce, healthcare, and social media. To address these tasks effectively, Relational Deep Learning (RDL) encodes relational data as graphs, enabling Graph Neural Networks (GNNs) to exploit relational structures for improved predictions. However, existing RDL methods often overlook the intrinsic structural properties of the graphs built from relational databases, leading to modeling inefficiencies, particularly in handling many-to-many relationships. Here we introduce RelGNN, a novel GNN framework specifically designed to leverage the unique structural characteristics of the graphs built from relational databases. At the core of our approach is the introduction of atomic routes, which are simple paths that enable direct single-hop interactions between the source and destination nodes. Building upon these atomic routes, RelGNN designs new composite message passing and graph attention mechanisms that reduce redundancy, highlight key signals, and enhance predictive accuracy. RelGNN is evaluated on 30 diverse real-world tasks from Relbench (Fey et al., 2024), and achieves state-of-the-art performance on the vast majority of tasks, with improvements of up to 25%. Code is available at https://github.com/snap-stanford/RelGNN.
Forward citations
Cited by 9 Pith papers
-
RelBench v2: A Large-Scale Benchmark and Repository for Relational Data
RelBench v2 expands a relational deep learning benchmark with four new large datasets and autocomplete tasks, showing models that use table relationships outperform single-table baselines.
-
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.
-
What Makes a Desired Graph for Relational Deep Learning?
Schema-derived graphs for relational deep learning suffer from information overload and semantic fragmentation; controlled filtering and injection via an end-to-end optimizer improves accuracy on 26 tasks while often ...
-
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.
-
TabPFN-3: Technical Report
TabPFN-3 delivers state-of-the-art tabular prediction performance on benchmarks up to 1M rows, is up to 20x faster than prior versions, and introduces test-time scaling that beats non-TabPFN models by hundreds of Elo points.
-
TabPFN-3: Technical Report
TabPFN-3 scales tabular foundation models to 1M rows with synthetic pretraining, test-time compute, and benchmark-leading performance on tabular, relational, and tabular-text tasks while being up to 20x faster than Ta...
-
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.
-
Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases
A SQL-like domain-specific language that declares predictive tasks on relational databases and automatically generates leakage-free training labels, with batch and low-latency implementations.
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.