Tracing Distribution Shifts with Causal System Maps

2025-10-27

AI Summary

Existing ML monitoring systems detect data distribution shifts but struggle to automatically identify their root causes—such as data defects, software failures, or genuine concept drift—relying instead on manual root-cause analysis. To address this, we propose a causal graph framework for ML systems, the first to integrate causal modeling with hierarchical system abstraction. It constructs a multi-granularity dependency graph spanning environmental variables, data pipelines, and model components. By analyzing propagation paths, the framework enables traceable attribution of distribution shifts back to their origins. This systematically establishes a mapping between observed distributional changes and their underlying causes, advancing ML monitoring from merely detecting *whether* a shift occurs to explaining *why* it occurs. The framework provides both theoretical foundations and a practical technical pathway toward interpretable, traceable, and automated ML monitoring. (149 words)

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Monitoring machine learning (ML) systems is hard, with standard practice focusing on detecting distribution shifts rather than their causes. Root-cause analysis often relies on manual tracing to determine whether a shift is caused by software faults, data-quality issues, or natural change. We propose ML System Maps -- causal maps that, through layered views, make explicit the propagation paths between the environment and the ML system's internals, enabling systematic attribution of distribution shifts. We outline the approach and a research agenda for its development and evaluation.

Problem

• Detecting causes of ML system distribution shifts
• Automating root-cause analysis for data quality issues
• Mapping causal propagation paths in ML systems

Innovation

• Causal maps visualize ML system environment interactions
• Layered views trace distribution shift propagation paths
• Systematic attribution replaces manual root-cause analysis