Database Views as Explanations for Relational Deep Learning

2025-09-11

AI Summary

Explaining predictions of deep learning models—such as heterogeneous graph neural networks—over relational databases remains challenging due to the structural complexity and semantic heterogeneity of relational data. Method: This paper proposes a view-based abductive explanation framework that introduces classical deterministic logic into explainable AI (XAI). It employs learnable masks to identify the most predictive data subsets and generates multi-granular, model-adaptive semantic views. To ensure scalability, the method integrates view-definition fragments with heuristic search, avoiding exhaustive enumeration over the entire database. Contribution/Results: Evaluated on multiple domain tasks from RelBench, the framework achieves high explanation accuracy and computational efficiency. It precisely identifies critical structured data patterns driving model predictions and delivers globally coherent, human-interpretable attributions grounded in relational semantics.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Statistical Relational/Logic Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In recent years, there has been significant progress in the development of deep learning models over relational databases, including architectures based on heterogeneous graph neural networks (hetero-GNNs) and heterogeneous graph transformers. In effect, such architectures state how the database records and links (e.g., foreign-key references) translate into a large, complex numerical expression, involving numerous learnable parameters. This complexity makes it hard to explain, in human-understandable terms, how a model uses the available data to arrive at a given prediction. We present a novel framework for explaining machine-learning models over relational databases, where explanations are view definitions that highlight focused parts of the database that mostly contribute to the model's prediction. We establish such global abductive explanations by adapting the classic notion of determinacy by Nash, Segoufin, and Vianu (2010). In addition to tuning the tradeoff between determinacy and conciseness, the framework allows controlling the level of granularity by adopting different fragments of view definitions, such as ones highlighting whole columns, foreign keys between tables, relevant groups of tuples, and so on. We investigate the realization of the framework in the case of hetero-GNNs. We develop heuristic algorithms that avoid the exhaustive search over the space of all databases. We propose techniques that are model-agnostic, and others that are tailored to hetero-GNNs via the notion of learnable masking. Our approach is evaluated through an extensive empirical study on the RelBench collection, covering a variety of domains and different record-level tasks. The results demonstrate the usefulness of the proposed explanations, as well as the efficiency of their generation.

Problem

• Explaining complex relational deep learning models' predictions
• Identifying key database parts contributing to model decisions
• Providing human-understandable view-based explanations for predictions

Innovation

• Database views as explanations for predictions
• Heuristic algorithms avoiding exhaustive database search
• Model-agnostic and hetero-GNN tailored techniques