4 papers · 1 filter
Parameter-Free Encoders Remain Viable for RDB Foundation Models
Linjie Xu, David Wipf
Given a relational database (RDB) storing heterogeneous tabular information, how can we predict missing (or future) values in some target column of interest? As the space of potent…
Griffin: Towards a Graph-Centric Relational Database Foundation Model
Yanbo Wang, Xiyuan Wang, Quan Gan +4
We introduce Griffin, the first foundation model attemptation designed specifically for Relational Databases (RDBs). Unlike previous smaller models focused on single RDB tasks, Gri…
Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners
Yuxin Wang, Botian Jiang, Yiran Guo +4
Prior-Fitted Networks (PFNs) have recently been proposed to efficiently perform tabular classification tasks. Although they achieve good performance on small datasets, they encount…
Efficient Link Prediction via GNN Layers Induced by Negative Sampling
Yuxin Wang, Xiannian Hu, Quan Gan +3
Graph neural networks (GNNs) for link prediction can loosely be divided into two broad categories. First, \emph{node-wise} architectures pre-compute individual embeddings for each…