By shifting computation from deep message passing to efficient meta-path aggregation, MetaRTL captures rich relational semantics while maintaining high efficiency.
Abstract
Relational table learning has gained increasing attention with the widespread use of relational databases. Existing methods typically rely on deep GNN or HGNN stacks, leading to high computational costs and limited performance on large real-world databases. We propose MetaRTL, a two-stage framework for scalable and expressive relational table learning. In the first stage, MetaRTL obtains initial table embeddings via lightweight pre-training. In the second stage, it performs non-parametric message passing to derive meta-path features, which are then aggregated by an attention module, MetaAttn. By shifting computation from deep message passing to efficient meta-path aggregation, MetaRTL captures rich relational semantics while maintaining high efficiency. Experiments on 10 real-world datasets across 24 tasks demonstrate the effectiveness of the proposed method.
This paper presents MetaSieve, a metapath selection layer that determines which metapaths to retain and which to prune, and shows that MetaSieve consistently reduces per-epoch training time by large margins while maintaining and often improving accuracy.
Fahim Shahriar Khan, Ashraf Aboulnaga· 0 citations
Tabular foundation models achieve state-of-the-art performance on single-table tasks without any training. Recent work suggests that they are also well-suited for relational learning via deep feature synthesis (DFS), which flattens a relational schema into a single table by adding aggregates of the other tables'columns...
PEARL augments the retrieval corpus offline by generating multi-hop queries over pre-identified join paths and reorganizing relevant columns into vertically partitioned corpus units, enabling effective multi-table retrieval without query-time LLM inference.
S. Ho, Hyeongu Kang, Seongku Kang et al.· 0 citations
EdgeReMIND sets the highest reported test mean reciprocal rank (MRR) on six of eight TGB 2.0 datasets and is the only relation-aware method that runs on all of them and is the only relation-aware method that runs on all of them.
This work proposes H2Table (Hierarchical Hypergraph-Enhanced Table Reasoning), a novel framework that represents complex tables as hierarchical nested hypergraphs, and designs a tailored hypergraph encoder to facilitate message passing between hyperedges and nodes within complex tables.
Jia Ling, Yang-Fan Wang, Chen Tang et al.· 0 citations
An open-source declarative language that streamlines RDL task formulation by abstracting away low-level SQL details, RTGL is introduced - an open-source declarative language that streamlines RDL task formulation by abstracting away low-level SQL details.
О. М. Колесниченко, Jakub Peleška, Gustav Šír· 0 citations
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
