Paper Detail

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

Kuo-Chung Peng, Jiun-Cheng Jiang, Chun-Hua Lin, Tai-Yue Li, Nan-Yow Chen, Samuel Yen-Chi Chen

huggingface Score 11.9

Published 2026-06-26 · First seen 2026-07-04

General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{peng2026parameter,
  title = {Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting},
  author = {Kuo-Chung Peng and Jiun-Cheng Jiang and Chun-Hua Lin and Tai-Yue Li and Nan-Yow Chen and Samuel Yen-Chi Chen},
  year = {2026},
  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 K},
  url = {https://huggingface.co/papers/2606.27821},
  keywords = {traffic matrices, quantum-inspired recurrent models, gated quantum-inspired Kolmogorov-Arnold network fast-weight programmers, QKAN-FWPs, multi-step forecasting, origin-destination matrix, long short-term memory, LSTM, classical gated fast-weight programmer, root-mean-square error, validation-loss area under learning curve, AULC, huggingface daily},
  eprint = {2606.27821},
  archiveprefix = {arXiv},
}

Metadata

{}