# TrafficKAN-GCN: Graph Convolutional-based Kolmogorov-Arnold Network for Traffic Flow Optimization

arXiv: https://arxiv.org/abs/2503.03276 · HTML: https://mlsanity.com/paper/2503.03276/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 72 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction](https://mlsanity.com/paper/1701.04245/) (2017)
- [KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning](https://mlsanity.com/paper/2406.18380/) (2024)
- [Kolmogorov-Arnold Networks: A Critical Assessment of Claims, Performance, and Practical Viability](https://mlsanity.com/paper/2407.11075/) (2024)
- [MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation](https://mlsanity.com/paper/2402.19407/) (2024)
- [Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis](https://mlsanity.com/paper/2408.07314/) (2024)
- [Superpixel-based and Spatially-regularized Diffusion Learning for Unsupervised Hyperspectral Image Clustering](https://mlsanity.com/paper/2312.15447/) (2023)
- [AlignGroup: Learning and Aligning Group Consensus with Member Preferences for Group Recommendation](https://mlsanity.com/paper/2409.02580/) (2024)
- [Human-oriented Representation Learning for Robotic Manipulation](https://mlsanity.com/paper/2310.03023/) (2023)
- [Joint Pedestrian Trajectory Prediction through Posterior Sampling](https://mlsanity.com/paper/2404.00237/) (2024)
- [An Integrated Transportation Distance Between Kernels and Approximate Dynamic Risk Evaluation in Markov Systems](https://mlsanity.com/paper/2311.06645/) (2023)
- [A predictive analytics approach for stroke prediction using machine learning and neural networks](https://mlsanity.com/paper/2203.00497/) (2022)
- [CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement](https://mlsanity.com/paper/2501.06441/) (2025)
- [Stereo Matching Based on Visual Sensitive Information](https://mlsanity.com/paper/2105.10831/) (2021)
- [DDUNet: Dual Dynamic U-Net for Highly-Efficient Cloud Segmentation](https://mlsanity.com/paper/2501.15385/) (2025)
- [Multi-Cali Anything: Dense Feature Multi-Frame Structure-from-Motion for Large-Scale Camera Array Calibration](https://mlsanity.com/paper/2503.00737/) (2025)
- [Exploring Human Mobility for Multi-Pattern Passenger Prediction: A Graph Learning Framework](https://mlsanity.com/paper/2202.10339/) (2022)
- [UCloudNet: A Residual U-Net with Deep Supervision for Cloud Image Segmentation](https://mlsanity.com/paper/2501.06440/) (2025)
- [Fast Dual Subgradient Optimization of the Integrated Transportation Distance Between Stochastic Kernels](https://mlsanity.com/paper/2312.01432/) (2023)
- [CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentation](https://mlsanity.com/paper/2501.15389/) (2025)

## Abstract (arXiv)

Urban traffic optimization is critical for improving transportation efficiency and alleviating congestion, particularly in large-scale dynamic networks. Traditional methods, such as Dijkstra's and Floyd's algorithms, provide effective solutions in static settings, but they struggle with the spatial-temporal complexity of real-world traffic flows. In this work, we propose TrafficKAN-GCN, a hybrid deep learning framework combining Kolmogorov-Arnold Networks (KAN) with Graph Convolutional Networks (GCN), designed to enhance urban traffic flow optimization. By integrating KAN's adaptive nonlinear function approximation with GCN's spatial graph learning capabilities, TrafficKAN-GCN captures both complex traffic patterns and topological dependencies. We evaluate the proposed framework using real-world traffic data from the Baltimore Metropolitan area. Compared with baseline models such as MLP-GCN, standard GCN, and Transformer-based approaches, TrafficKAN-GCN achieves competitive prediction accuracy while demonstrating improved robustness in handling noisy and irregular traffic data. Our experiments further highlight the framework's ability to redistribute traffic flow, mitigate congestion, and adapt to disruptive events, such as the Francis Scott Key Bridge collapse. This study contributes to the growing body of work on hybrid graph learning for intelligent transportation systems, highlighting the potential of combining KAN and GCN for real-time traffic optimization. Future work will focus on reducing computational overhead and integrating Transformer-based temporal modeling for enhanced long-term traffic prediction. The proposed TrafficKAN-GCN framework offers a promising direction for data-driven urban mobility management, balancing predictive accuracy, robustness, and computational efficiency.