LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G

2026-01-18

AI Summary

This work addresses the demand for high-precision prediction in near-real-time intelligent control for 6G open radio access networks, where conventional Transformers struggle due to their quadratic complexity under stringent latency and computational constraints. To overcome this, we propose a post-Transformer architecture that uniquely integrates quantum-inspired tensor train (TT)/matrix product state (MPS) decomposition with structured state space models, enabling linear-complexity long-sequence modeling. A lightweight channel gating mechanism and hybrid layers are introduced to capture dynamic dependencies among non-stationary key performance indicators. The proposed method achieves comparable prediction accuracy while reducing model parameters by 155× and accelerating inference by 2.74× relative to Transformers. It also outperforms existing state space baselines by being 10.8–15.8× smaller and 1.4× faster, significantly enhancing scalability and deployment efficiency.

Technology Category

• Machine Learning: Quantum Machine Learning
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Real-Time (Near-RT) latency and computational constraints. While Transformer-based models are effective for sequence modeling, their quadratic complexity limits scalability in Near-RT RAN Intelligent Controller (RIC) analytics. This paper investigates a post-Transformer design paradigm for efficient radio telemetry forecasting. We propose a quantum-inspired many-body state-space tensor network that replaces self-attention with stable structured state-space dynamics kernels, enabling linear-time sequence modeling. Tensor-network factorizations in the form of Tensor Train (TT) / Matrix Product State (MPS) representations are employed to reduce parameterization and data movement in both input projections and prediction heads, while lightweight channel gating and mixing layers capture non-stationary cross-Key Performance Indicator (KPI) dependencies. The proposed model is instantiated as an agentic perceive-predict xApp and evaluated on a bespoke O-RAN KPI time-series dataset comprising 59,441 sliding windows across 13 KPIs, using Reference Signal Received Power (RSRP) forecasting as a representative use case. Our proposed Linear Quantum-Inspired State-Space (LiQSS) model is 10.8x-15.8x smaller and approximately 1.4x faster than prior structured state-space baselines. Relative to Transformer-based models, LiQSS achieves up to a 155x reduction in parameter count and up to 2.74x faster inference, without sacrificing forecasting accuracy.

Problem

• 6G O-RAN
• Near-Real-Time control
• sequence modeling
• computational efficiency
• latency constraints

Innovation

• Quantum-inspired tensor networks
• Linear state-space models
• O-RAN xApp
• Near-Real-Time forecasting
• Parameter-efficient architecture