arXiv cs.AI· Sean Bin Yang, Zongyi Xu, Jilin Hu, Ying Sun, Kristian Torp, Bin Yang, Torben Bach Pedersen, Christian S. Jensen·· 12 小时前AI 评分22
PRISM：面向城市区域表示学习的自适应多视图融合框架
Rethinking Multi-View Fusion for Urban Representation Learning
AI 导读
PRISM 是一个自调整的多视图学习框架，用稀疏 MoE 路由学习区域专属的视图分配，并以受 PID 启发的调节机制缓解优化中的梯度冲突。研究指出城市数据存在模态效用随区域变化、异构目标梯度长期失衡两大结构性问题。在三个大规模城市数据集上，PRISM 性能与强多视图基线相当，同时优化更稳定、区域表示更均衡。
正文 · 原文
Abstract:Urban region representation learning encodes heterogeneous urban signals, such as mobility flows, points of interest, and land-use patterns, into unified embeddings for downstream tasks, including check-in prediction, crime forecasting, and service demand estimation. Existing approaches rely on globally shared fusion and joint optimization, implicitly assuming uniform modality importance and naturally balanced multi-objective training. However, urban data is inherently heterogeneous. Our empirical analysis reveals two structural issues: (i) modality utility varies markedly across regions, causing static fusion to overemphasize signals from certain modalities; and (ii) heterogeneous objectives exhibit persistent gradient imbalance, causing representational bias and unstable training. We present PRISM, a self-adjusting framework for adaptive multi-view learning. PRISM adapts sparse MoE routing to learn region-specific view allocations, while a PID (Proportional Integral Derivative)-inspired regulation mechanism mitigates gradient conflicts during optimization. Experiments on three large-scale urban datasets show that PRISM achieves competitive performance compared with strong multi-view baselines, while providing more stable optimization behavior and more balanced region representations.
| Comments: | Accepted by PVLDB 2027 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.31850 [cs.LG] |
| (or arXiv:2610.31850v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31850 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sean Bin Yang [view email]
[v1]
Thu, 22 Oct 2026 19:32:45 UTC (3,556 KB)
来源：arXiv cs.AI · arxiv.org