5 papers
AutoGrable: What Is a Good Graph for a Table?
Tamara Cucumides, Floris Geerts
Graph learning presupposes a graph, and tables and relational databases do not come with one. Applying a GNN to them requires deciding which entities become nodes, which of them to…
Latent Bridges for Multi-Table Question Answering
Simone Varriale, Tamara Cucumides, Floris Geerts +1
We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering. Our method lifts relational data into an heterogeneous graph, encodes it via message passing,…
Grables: When Graph Structure Helps Tabular Prediction
Tamara Cucumides, Floris Geerts
Simple row-wise predictors that score each row independently remain competitive with far more expressive architectures on tabular benchmarks, which are i.i.d. by construction. They…
From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNs
Tamara Cucumides, Floris Geerts
Tabular and relational data remain the most ubiquitous formats in real-world machine learning applications, spanning domains from finance to healthcare. Although both formats offer…
A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs
Tamara Cucumides, Daniel Daza, Pablo Barceló +4
The challenge of answering graph queries over incomplete knowledge graphs is gaining significant attention in the machine learning community. Neuro-symbolic models have emerged as…