SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objective

• URL: http://arxiv.org/abs/2604.07383v1
• Date: Wed, 08 Apr 2026 02:42:55 GMT
• Title: SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objective
• Abstract summary: Cross-city transfer improves prediction in label-scarce cities by leveraging labeled data from other cities.<n>We propose SCOT, a cross-city representation learning framework that learns explicit soft correspondences between unequal region sets.
• Score: 29.70837520752111
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cross-city transfer improves prediction in label-scarce cities by leveraging labeled data from other cities, but it becomes challenging when cities adopt incompatible partitions and no ground-truth region correspondences exist. Existing approaches either rely on heuristic region matching, which is often sensitive to anchor choices, or perform distribution-level alignment that leaves correspondences implicit and can be unstable under strong heterogeneity. We propose SCOT, a cross-city representation learning framework that learns explicit soft correspondences between unequal region sets via Sinkhorn-based entropic optimal transport. SCOT further sharpens transferable structure with an OT-weighted contrastive objective and stabilizes optimization through a cycle-style reconstruction regularizer. For multi-source transfer, SCOT aligns each source and the target to a shared prototype hub using balanced entropic transport guided by a target-induced prototype prior. Across real-world cities and tasks, SCOT consistently improves transfer accuracy and robustness, while the learned transport couplings and hub assignments provide interpretable diagnostics of alignment quality.

Related papers

• Reinforcement Learning-Guided Evolutionary Policy Optimization for Preference-Adjustable Heterogeneous Agile Earth Observation Satellite Scheduling [50.176885352114674]
  Heterogeneous agile Earth observation satellite (AEOS) scheduling requires task selection, satellite assignment, and observation sequencing.<n>This paper proposes an evolutionary policy optimization framework for heterogeneous AEOS scheduling with preference-adjustable weighted objectives.
  arXiv  Detail & Related papers  (2026-08-25T12:16:28Z)
• Coupled Optimal Transport with Landmark Constraints [64.98367856457412]
  An optimal transport (OT) model seeks a map or plan between distributions by minimizing a prescribed transport cost or distortion.<n>This paper proposes a novel coupled OT framework that leverages a small number of annotated landmarks to guide the recovery of an underlying deformation.<n>The proposed framework provides a principled connection between landmark-based registration and transport-based distribution matching.
  arXiv  Detail & Related papers  (2026-08-20T08:28:13Z)
• Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport [4.633342231489067]
  We propose a structure-preserving alignment framework, joint kernel entropic Gromov--Wasserstein Optimal Transport (JK-EGW)<n>JK-EGW maps multiple modalities into a common latent space by minimizing a quadratic optimal transport objective.<n>We show that our proposed method achieves improved multimodal retrieval performance compared to existing alignment baselines.
  arXiv  Detail & Related papers  (2026-08-04T21:21:09Z)
• CityGen: Structure-Guided City-Style Synthesis for Cross-City Autonomous Driving [5.149645190293104]
  CityTransfer-Bench is a benchmark for evaluating cross-city generalization across perception, segmentation, and planning.<n>CityGen is a diffusion-based generative framework that performs zero-label city adaptation via HD-map-conditioned synthesis guided by city-level visual prompts.
  arXiv  Detail & Related papers  (2026-05-28T13:46:48Z)
• TSC: Topology-Conditioned Stackelberg Coordination for Multi-Agent Reinforcement Learning in Interactive Driving [37.09409794849228]
  Topology-conditioned Stackelberg Coordination is a learning framework for decentralized interactive driving under communication-free execution.<n>We show that TSC achieves superior performance over representative MARL baselines across key metrics.
  arXiv  Detail & Related papers  (2026-02-27T10:46:41Z)
• Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents [102.21483770287985]
  We propose BrIdge contextual gap FoR imprOvised trajectory STeering (Bifrost) as a training-free method for self-improvement.<n>Bifrost consistently outperforms existing trajectory reuse and finetuned self-improvement methods.
  arXiv  Detail & Related papers  (2026-02-05T16:03:56Z)
• Optimal Transport-Based Decentralized Multi-Agent Distribution Matching [0.0]
  Decentralized framework for distribution matching in multi-agent systems.<n>Problem is formulated using optimal transport (Wasserstein distance)<n>System operates fully in a decentralized manner.
  arXiv  Detail & Related papers  (2026-01-02T03:35:25Z)
• Deep Neural Network-Based Aerial Transport in the Presence of Cooperative and Uncooperative UAS [3.437656066916039]
  We present a resilient deep neural network (DNN) framework for decentralized transport and coverage using uncrewed aerial systems (UAS) operating in $mathbbRn$.<n>The framework is explicitly designed to remain robust in the presence of uncooperative agents that deviate from or refuse to follow the prescribed protocol.
  arXiv  Detail & Related papers  (2025-12-06T22:03:41Z)
• Optimal Transport Adapter Tuning for Bridging Modality Gaps in Few-Shot Remote Sensing Scene Classification [80.83325513157637]
  Few-Shot Remote Sensing Scene Classification (FS-RSSC) presents the challenge of classifying remote sensing images with limited labeled samples.<n>We propose a novel Optimal Transport Adapter Tuning (OTAT) framework aimed at constructing an ideal Platonic representational space.
  arXiv  Detail & Related papers  (2025-03-19T07:04:24Z)
• Joint Optimal Transport and Embedding for Network Alignment [66.49765320358361]
  We propose a joint optimal transport and embedding framework for network alignment named JOENA.<n>With a unified objective, the mutual benefits of both methods can be achieved by an alternating optimization schema with guaranteed convergence.<n>Experiments on real-world networks validate the effectiveness and scalability of JOENA, achieving up to 16% improvement in MRR and 20x speedup.
  arXiv  Detail & Related papers  (2025-02-26T17:28:08Z)
• CityLight: A Neighborhood-inclusive Universal Model for Coordinated City-scale Traffic Signal Control [23.5766158697276]
  CityLight learns a universal policy based on representations obtained with two major modules.<n>Experiments on five city-scale datasets, ranging from 97 to 13,952 intersections, confirm the efficacy of CityLight.
  arXiv  Detail & Related papers  (2024-06-04T09:10:14Z)
• InfoOT: Information Maximizing Optimal Transport [58.72713603244467]
  InfoOT is an information-theoretic extension of optimal transport. It maximizes the mutual information between domains while minimizing geometric distances. This formulation yields a new projection method that is robust to outliers and generalizes to unseen samples.
  arXiv  Detail & Related papers  (2022-10-06T18:55:41Z)
• Comparing Probability Distributions with Conditional Transport [63.11403041984197]
  We propose conditional transport (CT) as a new divergence and approximate it with the amortized CT (ACT) cost. ACT amortizes the computation of its conditional transport plans and comes with unbiased sample gradients that are straightforward to compute. On a wide variety of benchmark datasets generative modeling, substituting the default statistical distance of an existing generative adversarial network with ACT is shown to consistently improve the performance.
  arXiv  Detail & Related papers  (2020-12-28T05:14:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.