Context-Aware Doubly-Robust Semi-Supervised Learning

2025-02-21

AI Summary

Next-generation communication systems face highly heterogeneous traffic and network environments, demanding high-fidelity contextual data for effective learning. Method: This paper proposes a context-aware, doubly robust semi-supervised learning framework that dynamically adjusts reliance on pseudo-labels generated by Network Digital Twins (NDTs), adapting to varying NDT fidelity across scenarios. It innovatively integrates doubly robust estimation from causal inference with a context-adaptive weighting mechanism to enable dynamic credibility assessment and bias correction of pseudo-labels. Contribution/Results: The framework overcomes the strong assumptions on pseudo-label quality inherent in conventional semi-supervised methods. Evaluated on downlink beamforming, it significantly outperforms state-of-the-art semi-supervised approaches, maintaining robust, high performance even under low-fidelity NDT conditions.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

The widespread adoption of artificial intelligence (AI) in next-generation communication systems is challenged by the heterogeneity of traffic and network conditions, which call for the use of highly contextual, site-specific, data. A promising solution is to rely not only on real-world data, but also on synthetic pseudo-data generated by a network digital twin (NDT). However, the effectiveness of this approach hinges on the accuracy of the NDT, which can vary widely across different contexts. To address this problem, this paper introduces context-aware doubly-robust (CDR) learning, a novel semi-supervised scheme that adapts its reliance on the pseudo-data to the different levels of fidelity of the NDT across contexts. CDR is evaluated on the task of downlink beamforming, showing superior performance compared to previous state-of-the-art semi-supervised approaches.

Problem

• Enhancing AI in communication systems
• Improving accuracy of network digital twins
• Optimizing downlink beamforming with CDR learning

Innovation

• Context-aware doubly-robust learning
• Semi-supervised scheme adaptation
• Network digital twin fidelity