Learning Semantic Association Rules from Internet of Things Data

2024-12-04

arXiv.org

AI Summary

Existing association rule mining (ARM) methods for IoT data overlook static domain knowledge—such as knowledge graphs—despite the heterogeneity and scale of IoT streams. Method: We propose an end-to-end semantic ARM framework that tightly integrates dynamic sensor streams with static knowledge graph metadata, leveraging variational autoencoders, knowledge graph embedding, and semantic rule compilation. Its core innovation is Aerial—a novel neuro-symbolic collaborative autoencoder for rule extraction—that explicitly models the decoder’s reconstruction process as rule generation, balancing generalizability and conciseness. Contribution/Results: Evaluated on three cross-domain IoT datasets, our framework achieves 100% rule coverage, compresses rule sets by 37%–62%, and significantly outperforms state-of-the-art methods in rule quality, demonstrating superior interpretability, scalability, and domain-awareness.

Technology Category

• Data Mining & Knowledge Management: Rule Mining & Pattern Mining
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Machine Learning: Neuro-Symbolic Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Association Rule Mining (ARM) is the task of discovering commonalities in data in the form of logical implications. ARM is used in the Internet of Things (IoT) for different tasks including monitoring and decision-making. However, existing methods give limited consideration to IoT-specific requirements such as heterogeneity and volume. Furthermore, they do not utilize important static domain-specific description data about IoT systems, which is increasingly represented as knowledge graphs. In this paper, we propose a novel ARM pipeline for IoT data that utilizes both dynamic sensor data and static IoT system metadata. Furthermore, we propose an Autoencoder-based Neurosymbolic ARM method (Aerial) as part of the pipeline to address the high volume of IoT data and reduce the total number of rules that are resource-intensive to process. Aerial learns a neural representation of a given data and extracts association rules from this representation by exploiting the reconstruction (decoding) mechanism of an autoencoder. Extensive evaluations on 3 IoT datasets from 2 domains show that ARM on both static and dynamic IoT data results in more generically applicable rules while Aerial can learn a more concise set of high-quality association rules than the state-of-the-art with full coverage over the datasets.

Problem

• Mining association rules from heterogeneous IoT data sources
• Addressing IoT-specific challenges like data volume and heterogeneity
• Incorporating static knowledge graphs with dynamic sensor data

Innovation

• Uses dynamic sensor and static metadata
• Autoencoder-based neurosymbolic method for rule extraction
• Learns concise high-quality rules with full coverage