Neural Canonical Polyadic Factorization for Traffic Analysis

TL;DR

This paper introduces NCPF, a neural tensor factorization model that effectively imputes missing traffic data by combining low-rank tensor algebra with deep learning, enhancing urban traffic analysis and management.

Contribution

The paper presents a novel neural CP tensor factorization model that integrates interpretable tensor decomposition with deep learning for robust traffic data imputation.

Findings

NCPF outperforms six state-of-the-art baselines on six urban traffic datasets.

The model effectively captures complex spatiotemporal traffic patterns.

NCPF provides a flexible framework for high-dimensional traffic data analysis.

Abstract

Modern intelligent transportation systems rely on accurate spatiotemporal traffic analysis to optimize urban mobility and infrastructure resilience. However, pervasive missing data caused by sensor failures and heterogeneous sensing gaps fundamentally hinders reliable traffic modeling. This paper proposes a Neural Canonical Polyadic Factorization (NCPF) model that synergizes low-rank tensor algebra with deep representation learning for robust traffic data imputation. The model innovatively embeds CP decomposition into neural architecture through learnable embedding projections, where sparse traffic tensors are encoded into dense latent factors across road segments, time intervals, and mobility metrics. A hierarchical feature fusion mechanism employs Hadamard products to explicitly model multilinear interactions, while stacked multilayer perceptron layers nonlinearly refine these representations to capture complex spatiotemporal couplings. Extensive evaluations on six urban traffic datasets demonstrate NCPF's superiority over six state-of-the-art baselines. By unifying CP decomposition's interpretable factor analysis with neural network's nonlinear expressive power, NCPF provides a principled yet flexible approaches for high-dimensional traffic data imputation, offering critical support for next-generation transportation digital twins and adaptive traffic control systems.