aiqbench analysis
This paper introduces MARCUS, a novel machine learning framework that reframes missing urban data not as noise but as a valuable contextual signal for region representation. By integrating intra- and inter-modal learning stages, the model significantly improves rent prediction accuracy on real-world datasets from Sydney and New York. The approach offers a robust methodological advance for handling incomplete multimodal data in complex urban analytics tasks.
MARCUS: Missing-Aware Region Representation with Contextual Urban Signals for Rent Prediction
arXiv:2608.18546v1 Announce Type: new Abstract: Multimodal urban data has expanded the applications of urban region representation learning, such as functional zone identification and real estate appraisal, but also introduces challenges caused by data incompleteness. Existing studies usually handle missing data through imputation, treating missingness as noise while ignoring its potential semantic value. To address this issue, we propose MARCUS, a missing-aware region representation model that treats missingness as a contextual urban signal. MARCUS models missingness in three stages: Intra Learning jointly encodes observed features and missing patterns, Inter Learning estimates modality reliability to guide cross-modal interaction, and Fusion uses missing-aware and time-aware gating to generate the final region embedding. We apply MARCUS to rent prediction, a task with long-term trends and seasonal fluctuations, using real-world datasets from Sydney and New York. Experimental results show that MARCUS achieves state-of-the-art performance, reducing MAE by 51.35% on Sydney and 12.62% on New York compared with the best baselines. Additional experiments, including an imputation-based ablation study and randomized additional-missingness analysis, further demonstrate the effectiveness of the proposed method.
Abstract:Multimodal urban data has expanded the applications of urban region representation learning, such as functional zone identification and real estate appraisal, but also introduces challenges caused by data incompleteness. Existing studies usually handle missing data through imputation, treating missingness as noise while ignoring its potential semantic value. To address this issue, we propose MARCUS, a missing-aware region representation model that treats missingness as a contextual urban signal. MARCUS models missingness in three stages: Intra Learning jointly encodes observed features and missing patterns, Inter Learning estimates modality reliability to guide cross-modal interaction, and Fusion uses missing-aware and time-aware gating to generate the final region embedding. We apply MARCUS to rent prediction, a task with long-term trends and seasonal fluctuations, using real-world datasets from Sydney and New York. Experimental results show that MARCUS achieves state-of-the-art performance, reducing MAE by 51.35% on Sydney and 12.62% on New York compared with the best baselines. Additional experiments, including an imputation-based ablation study and randomized additional-missingness analysis, further demonstrate the effectiveness of the proposed method.
10 pages, 7 figures, 4 tables. Accepted at the 2026 IEEE International Conference on Data Mining (ICDM 2026)
Machine Learning (cs.LG)
arXiv:2608.18546 [cs.LG]
(or arXiv:2608.18546v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.18546 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 281 words
Related coverage
When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning
arXiv · Sep 16, 2026
EEG-JEPA: Structured Latent Prediction for EEG Foundation Models
arXiv · Aug 5, 2026
Dharma vs Adharma - The Perplexity of Being Alive
hillpost.in · Aug 25, 2026
Triton-Based Optimization of Video Sparse Attention on ROCm
AMD · Jul 13, 2026