← Back to all news
arXiv Machine Learning By Weichen Li, Ken Zhong, Zheng Wang, Li Pan, Jianhua Li

InRTL: Effective Intra-Inter Interaction Learning for Relational Tables

Read the original on arXiv Machine Learning →

InRTL: Effective Intra-Inter Interaction Learning for Relational Tables proposes a unified framework that explicitly models dependencies both within and across relational tables. The approach introduces intra-table interactions to capture associations among rows in the same table and inter-table interactions to capture dependencies between rows linked by primary key–foreign key relationships. It employs a column-aware table encoder, Transformer-based self-attention and cross-attention modules, and incorporates linearized attention and heterogeneous graph neural networks to improve scalability, demonstrating effectiveness across ten datasets and 24 real-world tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 18

MetaRTL: Meta-path Attention Enhanced Relational Table Learning

MetaRTL is a two-stage framework for relational table learning that first generates lightweight pre-trained table embeddings and then applies non‑parametric message passing to extract meta‑path features. These features are aggregated using an attention module called MetaAttn, shifting computation from deep GNN stacks to efficient meta‑path aggregation. Experiments on 10 real‑world datasets across 24 tasks show that MetaRTL achieves strong performance while reducing computational cost.

By Ken Zhong, Weichen Li, Zheng Wang
rag
More like this →
arXiv AI
Sep 2

H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning

H2Table introduces a hierarchical hypergraph representation for complex tables, enabling a hypergraph encoder to capture semantic relationships between headers and cells. The framework uses learnable query vectors to extract structural embeddings for large language models. Experiments on the HiTab dataset show a 22.88% improvement over state‑of‑the‑art baselines on tables with four levels of nesting.

By Jia Ling, Yangfan Wang, Chen Tang, Haoming Tan, Yang Yang, Yi Guan, Jingchi Jiang
llmsragnlpbenchmarks
More like this →