Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting

2026-06-26

AI Summary

This work addresses the challenge of achieving high-accuracy full-matrix traffic prediction under stringent constraints on memory, update frequency, and training budget in online network control scenarios. The authors propose a quantum-inspired recurrent architecture—termed Gated Quantum Kolmogorov–Arnold Network Fast Weight Programmer (G-QKANFWP)—which integrates a gated fast weight mechanism with a multi-step origin–destination (OD) matrix prediction framework, eschewing reliance on graph neural networks, Transformers, or diffusion modules. Despite employing only 22.4% of the parameters of a large LSTM baseline, the proposed method substantially reduces root mean square error (RMSE) and outperforms existing approaches in both channel-level prediction win rate and area under the validation loss curve, effectively balancing computational efficiency with predictive accuracy.

Abstract

Traffic matrices (TMs) capture network-wide origin-destination demand and are central to traffic engineering, yet accurate whole-matrix forecasting remains challenging when prediction must be performed under the memory, update, and training-budget constraints of online network control. This paper investigates whether compact quantum-inspired recurrent models can provide effective TM forecasts without relying on dedicated graph, transformer, or diffusion modules. We adapt gated quantum-inspired Kolmogorov-Arnold network fast-weight programmers (QKAN-FWPs) to direct multi-step Abilene TM forecasting, where each model predicts the next 20 five-minute frames of a 144-channel origin-destination (OD) matrix from a two-hour history. We benchmark three QKAN placement variants against a matched-size long short-term memory (LSTM) network, a larger LSTM, and a classical gated fast-weight programmer under a shared fixed-budget training protocol. Among the evaluated recurrent models, G-QKANFWP achieves the best pooled root-mean-square error (RMSE), while using only 22.4% of the larger LSTM. It also outperforms both the matched-size LSTM and the classical G-FWP baseline, indicating that the gain is not due to gated fast-weight framework alone. Convergence and channel-wise analyses further show that the quantum-inspired variants obtain lower validation-loss area under the learning curve (AULC) than matched-size recurrent baselines, while G-QKANFWP and GQKAN-FWP achieve substantially more OD-channel wins. These results identify a classical slow programmer with a quantum-inspired fast programmer as a promising accuracy-efficiency design for resource-conscious network traffic-matrix forecasting.

Problem

• Traffic-Matrix Forecasting
• Parameter Efficiency
• Online Network Control
• Resource-Constrained Prediction
• Quantum-Inspired Models

Innovation

• quantum-inspired
• fast-weight programmer
• Kolmogorov-Arnold network
• traffic matrix forecasting
• parameter-efficient