A Pre-training Framework for Relational Data with Information-theoretic Principles

• URL: http://arxiv.org/abs/2507.09837v1
• Date: Mon, 14 Jul 2025 00:17:21 GMT
• Title: A Pre-training Framework for Relational Data with Information-theoretic Principles
• Authors: Quang Truong, Zhikai Chen, Mingxuan Ju, Tong Zhao, Neil Shah, Jiliang Tang,
• Abstract summary: We introduce Task Vector Estimation (TVE), a novel pre-training framework that constructs supervisory signals via set-based aggregation over relational graphs.<n>TVE consistently outperforms traditional pre-training baselines.<n>Our findings advocate for pre-training objectives that encode task heterogeneity and temporal structure as design principles for predictive modeling on relational databases.
• Score: 57.93973948947743
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Relational databases underpin critical infrastructure across a wide range of domains, yet the design of generalizable pre-training strategies for learning from relational databases remains an open challenge due to task heterogeneity. Specifically, there exist infinitely many possible downstream tasks, as tasks are defined based on relational schema graphs, temporal dependencies, and SQL-defined label logics. An effective pre-training framework is desired to take these factors into account in order to obtain task-aware representations. By incorporating knowledge of the underlying distribution that drives label generation, downstream tasks can benefit from relevant side-channel information. To bridge this gap, we introduce Task Vector Estimation (TVE), a novel pre-training framework that constructs predictive supervisory signals via set-based aggregation over schema traversal graphs, explicitly modeling next-window relational dynamics. We formalize our approach through an information-theoretic lens, demonstrating that task-informed representations retain more relevant signals than those obtained without task priors. Extensive experiments on the RelBench benchmark show that TVE consistently outperforms traditional pre-training baselines. Our findings advocate for pre-training objectives that encode task heterogeneity and temporal structure as design principles for predictive modeling on relational databases.

Related papers

• Task-Agnostic Contrastive Pretraining for Relational Deep Learning [0.0]
  We propose a novel task-agnostic contrastive pretraining approach for RDL that enables database-wide representation learning.<n>We implement the respective pretraining approach through a modular RDL architecture.<n>Our preliminary results demonstrate that finetuning the pretrained models measurably outperforms training from scratch.
  arXiv  Detail & Related papers  (2025-06-27T13:18:13Z)
• Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures [50.46688111973999]
  Graph machine learning has led to a significant increase in the capabilities of models that learn on arbitrary graph-structured data.<n>We present a new blueprint that enables end-to-end representation of'relational entity graphs' without traditional engineering feature.<n>We discuss key challenges including large-scale multi-table integration and the complexities of modeling temporal dynamics and heterogeneous data.
  arXiv  Detail & Related papers  (2025-06-19T23:51:38Z)
• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [55.914891182214475]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• Boosting Relational Deep Learning with Pretrained Tabular Models [18.34233986830027]
  Graph Neural Networks (GNNs) offer a compelling alternative inherently by modeling these relationships.<n>Our framework achieves up to $33%$ performance improvement and a $526times$ inference speedup compared to GNNs.
  arXiv  Detail & Related papers  (2025-04-07T11:19:04Z)
• A representational framework for learning and encoding structurally enriched trajectories in complex agent environments [1.904851064759821]
  The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex scenarios.<n>One way to address this issue has focused on learning efficient representations of the world and on how the actions of agents affect them, such as disentangled representations that exploit symmetries.<n>We propose to enrich the agent's ontology and extend the traditionalisation of trajectories to provide a more nuanced view of task execution.
  arXiv  Detail & Related papers  (2025-03-17T14:04:27Z)
• Meta-Statistical Learning: Supervised Learning of Statistical Inference [59.463430294611626]
  This work demonstrates that the tools and principles driving the success of large language models (LLMs) can be repurposed to tackle distribution-level tasks.<n>We propose meta-statistical learning, a framework inspired by multi-instance learning that reformulates statistical inference tasks as supervised learning problems.
  arXiv  Detail & Related papers  (2025-02-17T18:04:39Z)
• RelGNN: Composite Message Passing for Relational Deep Learning [56.48834369525997]
  We introduce RelGNN, a novel GNN framework specifically designed to leverage the unique structural characteristics of the graphs built from relational databases.<n>RelGNN is evaluated on 30 diverse real-world tasks from Relbench (Fey et al., 2024), and achieves state-of-the-art performance on the vast majority tasks, with improvements of up to 25%.
  arXiv  Detail & Related papers  (2025-02-10T18:58:40Z)
• RelBench: A Benchmark for Deep Learning on Relational Databases [78.52438155603781]
  We present RelBench, a public benchmark for solving tasks over databases with graph neural networks. We use RelBench to conduct the first comprehensive study of Deep Learning infrastructure. RDL learns better whilst reducing human work needed by more than an order of magnitude.
  arXiv  Detail & Related papers  (2024-07-29T14:46:13Z)
• ConstGCN: Constrained Transmission-based Graph Convolutional Networks for Document-level Relation Extraction [24.970508961370548]
  Document-level relation extraction with graph neural networks faces a fundamental graph construction gap between training and inference. We propose $textbfConstGCN$, a novel graph convolutional network which performs knowledge-based information propagation between entities. Experimental results show that our method outperforms the previous state-of-the-art (SOTA) approaches on the DocRE dataset.
  arXiv  Detail & Related papers  (2022-10-08T07:36:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.