# OpFlow: Learning Opportunity-Conditioned Choice Potentials for Robust OD Flow Prediction

arXiv: https://arxiv.org/abs/2607.03200 · HTML: https://mlsanity.com/paper/2607.03200/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Deep Gravity: enhancing mobility flows generation with deep neural networks and geographic information](https://mlsanity.com/paper/2012.00489/) (2020)
- [Complexity-aware Large Scale Origin-Destination Network Generation via Diffusion Model](https://mlsanity.com/paper/2306.04873/) (2023)
- [Origin-Destination Network Generation via Gravity-Guided GAN](https://mlsanity.com/paper/2306.03390/) (2023)
- [Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction](https://mlsanity.com/paper/2206.15005/) (2022)
- [Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenario](https://mlsanity.com/paper/2410.04740/) (2024)

## Built on by (most cited first, 1 of 1)

- [Learning Deployable Causal Action Geometry under Temporal Non-Stationarity](https://mlsanity.com/paper/2610.16644/) (2026)

## Abstract (arXiv)

Origin-destination (OD) flow prediction is central to urban analytics, yet deep models trained on raw counts remain vulnerable to distribution shift. The core problem is that raw count supervision cannot distinguish transferable choice mechanisms from environment-specific shortcuts. Raw OD count mixes two objects: how much demand an origin produces and how that demand is allocated across destinations. We argue that the transferable object is the exposure-to-choice law that maps spatial conditions to relative destination preferences. We propose OpFlow, a mechanism-constrained framework that learns row-centered choice potentials and reconstructs flows by combining the induced allocation with a separately calibrated origin scale. Under distribution shift, spatial exposures and the induced allocations are allowed to vary; what transfers is the conditional map from exposure states to relative choice potentials. Theoretically, we characterize the identifiable row-centered potential and show that classical spatial interaction laws are restricted log-potential cases. Controlled synthetic shifts and a real-world experiment show OpFlow improves robustness under environment shifts.