Dynamic Features Adaptation in Networking: Toward Flexible training and Explainable inference

2025-10-09

AI Summary

To address data distribution drift and dynamic feature adaptation challenges arising from multi-vendor deployment, hardware upgrades, and service evolution in 6G networks, this paper proposes the Drift-Aware Feature Importance (DAFI) framework. DAFI integrates distribution drift detection, Adaptive Random Forest (ARF)-based incremental learning, and an XAI-driven mechanism for dynamic scheduling of lightweight versus complex feature importance computations. It triggers high-cost importance estimation only upon detecting statistically significant drift, thereby preserving explanation consistency while improving computational efficiency; ARF ensures stable online learning and progressive performance refinement. Experiments on three real-world 6G network datasets demonstrate that DAFI reduces feature importance computation time by up to 2×, significantly enhances result consistency across time, and achieves a balanced trade-off among efficiency, stability, and interpretability.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Distributed Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

As AI becomes a native component of 6G network control, AI models must adapt to continuously changing conditions, including the introduction of new features and measurements driven by multi-vendor deployments, hardware upgrades, and evolving service requirements. To address this growing need for flexible learning in non-stationary environments, this vision paper highlights Adaptive Random Forests (ARFs) as a reliable solution for dynamic feature adaptation in communication network scenarios. We show that iterative training of ARFs can effectively lead to stable predictions, with accuracy improving over time as more features are added. In addition, we highlight the importance of explainability in AI-driven networks, proposing Drift-Aware Feature Importance (DAFI) as an efficient XAI feature importance (FI) method. DAFI uses a distributional drift detector to signal when to apply computationally intensive FI methods instead of lighter alternatives. Our tests on 3 different datasets indicate that our approach reduces runtime by up to 2 times, while producing more consistent feature importance values. Together, ARFs and DAFI provide a promising framework to build flexible AI methods adapted to 6G network use-cases.

Problem

• Adapting AI models to dynamic feature changes in 6G networks
• Ensuring stable predictions through iterative training with ARFs
• Providing explainable inference via efficient feature importance methods

Innovation

• Adaptive Random Forests enable flexible training in dynamic networks
• Drift-Aware Feature Importance optimizes explainable AI inference
• Combined framework reduces runtime while maintaining prediction accuracy