Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputation

2026-01-08

arXiv.org

AI Summary

This work addresses the limitation of existing diffusion models in traffic data imputation, which employ fixed spatiotemporal guidance scales and struggle to adapt to nodes with high missing rates, often yielding distorted reconstructions. To overcome this, we propose FENCE, a novel method that introduces a posterior likelihood–based dynamic feedback mechanism to adaptively modulate guidance strength. By integrating attention-based clustering, FENCE enables node-level fine-grained control over the conditional generation process across both spatial and temporal dimensions. Extensive experiments on multiple real-world traffic datasets demonstrate that FENCE significantly outperforms current diffusion-based approaches and other state-of-the-art methods, achieving markedly improved imputation accuracy under high-missing-rate scenarios.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• 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
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Imputing missing values in spatial-temporal traffic data is essential for intelligent transportation systems. Among advanced imputation methods, score-based diffusion models have demonstrated competitive performance. These models generate data by reversing a noising process, using observed values as conditional guidance. However, existing diffusion models typically apply a uniform guidance scale across both spatial and temporal dimensions, which is inadequate for nodes with high missing data rates. Sparse observations provide insufficient conditional guidance, causing the generative process to drift toward the learned prior distribution rather than closely following the conditional observations, resulting in suboptimal imputation performance. To address this, we propose FENCE, a spatial-temporal feedback diffusion guidance method designed to adaptively control guidance scales during imputation. First, FENCE introduces a dynamic feedback mechanism that adjusts the guidance scale based on the posterior likelihood approximations. The guidance scale is increased when generated values diverge from observations and reduced when alignment improves, preventing overcorrection. Second, because alignment to observations varies across nodes and denoising steps, a global guidance scale for all nodes is suboptimal. FENCE computes guidance scales at the cluster level by grouping nodes based on their attention scores, leveraging spatial-temporal correlations to provide more accurate guidance. Experimental results on real-world traffic datasets show that FENCE significantly enhances imputation accuracy.

Problem

• traffic imputation
• missing data
• diffusion models
• spatial-temporal data
• guidance scale

Innovation

• diffusion models
• spatial-temporal imputation
• adaptive guidance
• feedback mechanism
• traffic data