Relational Deep Learning (RDL) enables predictive learning directly on relational databases by representing tables and foreign-key relationships as heterogeneous graphs. RelBench provides a benchmark for evaluating such models across databases with different schemas and downstream prediction tasks [1]. Heterogeneous Graph Neural Networks (GNNs), such as HGT [2], can model typed relationships, but their schema-dependent representations make transferring pretrained models across databases challenging.<\/p>\n\n\n\n
Recent studies have explored self-supervised graph pretraining [3], cross-domain graph pretraining [4, 5], and transferable graph reasoning [6]. However, how to identify and share compatible relations across different database schemas remains insufficiently explored. In particular, existing approaches do not systematically investigate how relation abstraction and importance-based selection affect information preservation, transferability, and negative transfer.<\/p>\n\n\n\n
This thesis aims to develop a cross-schema relation abstraction framework that characterizes, groups, and selectively preserves relations based on their structural properties. By constructing a shared relation representation space, the framework enables mixed GNN pretraining across multiple RelBench databases and investigates the following research questions:<\/p>\n\n\n\n
Research Questions:<\/strong><\/p>\n\n\n\n RQ1 \u2014 Relation Abstraction: How can structural and statistical characteristics of relations be used to construct a shared relation representation space across different database schemas?<\/p>\n\n\n\n RQ2 \u2014 Cross-Schema Transferability: Can mixed pretraining across multiple databases improve downstream predictive performance on both seen and unseen schemas compared with random initialization and single-database pretraining?<\/p>\n\n\n\n RQ3 \u2014 Abstraction and Selection: How do relation abstraction and importance-based selection individually and jointly affect information preservation, transferability, and negative transfer?<\/p>\n\n\n\n RQ4 \u2014 Computational Efficiency: Can shared pretraining improve the trade-off between predictive performance and computational cost, including pretraining and downstream adaptation overhead?<\/p>\n\n\n\n <\/p>\n","protected":false},"excerpt":{"rendered":" Relational Deep Learning (RDL) enables predictive learning directly on relational databases by representing tables and foreign-key relationships as heterogeneous graphs. RelBench provides a benchmark for evaluating such models across databases with different schemas and downstream prediction tasks [1]. Heterogeneous Graph Neural Networks (GNNs), such as HGT [2], can model typed relationships, but their schema-dependent representations […]<\/p>\n","protected":false},"author":145,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[21],"tags":[90,87,46],"class_list":["post-7495","post","type-post","status-publish","format-standard","hentry","category-thesis","tag-attention-residuals","tag-commonsense-qa","tag-llm"],"acf":[],"_links":{"self":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/7495","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/users\/145"}],"replies":[{"embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/comments?post=7495"}],"version-history":[{"count":1,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/7495\/revisions"}],"predecessor-version":[{"id":7496,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/7495\/revisions\/7496"}],"wp:attachment":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/media?parent=7495"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/categories?post=7495"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/tags?post=7495"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}